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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. GPT2-Small
    3. Transcoders Residuals
    4. 8-TRES-DC
    5. 758
    Prev
    Next
    INDEX
    Explanations

    variations of the word "whole"

    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
    bi
    -0.71
    Frag
    -0.69
    zi
    -0.66
    Sense
    -0.66
     Reloaded
    -0.63
    Compat
    -0.63
    Ing
    -0.62
    bf
    -0.60
    BY
    -0.60
    cing
    -0.60
    POSITIVE LOGITS
    oak
    0.86
    heartedly
    0.82
    quartered
    0.78
    hearted
    0.72
     scalp
    0.67
    estyles
    0.66
     outfit
    0.65
    ngth
    0.63
    ffield
    0.63
     ethos
    0.62
    Activations Density 0.017%

    No Known Activations