© 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
    3. GPT2-Small
    5. Transcoders Residuals
    7. 8-TRES-DC
    9. 790
    Prev
    Next
    INDEX
    Explanations

    phrases indicating comparisons or measures of degree

    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
    ][/
    -0.69
     newsletters
    -0.67
     beads
    -0.64
     disob
    -0.62
     [+
    -0.62
    ppo
    -0.61
     emit
    -0.61
     Crack
    -0.59
     prose
    -0.59
     //[
    -0.59
    POSITIVE LOGITS
    ウス
    0.81
    龍契士
    0.80
     proport
    0.77
    ministic
    0.74
    med
    0.72
    ibaba
    0.71
    isite
    0.70
     tally
    0.65
     determination
    0.64
    conserv
    0.64
    Activations Density 0.037%

    No Known Activations