© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. GPT2-Small
    5. Transcoders Residuals
    7. 8-TRES-DC
    9. 1073
    Prev
    Next
    INDEX
    Explanations

    prepositions and their frequency of use

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ��
    -0.81
    ENA
    -0.81
    ツ
    -0.75
    TAIN
    -0.75
    �
    -0.73
    ASE
    -0.72
    aution
    -0.71
    atre
    -0.71
    ADRA
    -0.70
    inar
    -0.70
    POSITIVE LOGITS
     sclerosis
    0.73
     TRUE
    0.60
     junk
    0.60
     Flo
    0.59
     whistleblowers
    0.58
     darling
    0.58
     Junk
    0.58
     successors
    0.57
     select
    0.56
     heirs
    0.55
    Activations Density 0.138%

    No Known Activations