Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    words related to diversification and simplification in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    axe
    -0.16
    IZE
    -0.15
    ISED
    -0.15
    lder
    -0.14
    etre
    -0.14
     Fault
    -0.14
    à¹Ģสà¸Ļ
    -0.14
     Fulton
    -0.14
    Cached
    -0.14
    /inet
    -0.14
    POSITIVE LOGITS
    ification
    0.67
    ifying
    0.63
    ified
    0.60
    ifi
    0.54
    ify
    0.53
    ifications
    0.53
    ifier
    0.52
    if
    0.50
    ifies
    0.50
    ifiers
    0.49
    Act Density 0.052%

    No Known Activations