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

    Neuronpedia

    INDEX
    Explanations

    words related to transitions or changes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    TriState
    -0.16
    stav
    -0.16
    ROC
    -0.15
    oley
    -0.15
    sed
    -0.15
     Pig
    -0.14
    oled
    -0.14
    erral
    -0.14
    och
    -0.14
    zl
    -0.14
    POSITIVE LOGITS
    ist
    0.15
     conserv
    0.15
    CEPT
    0.15
    ivid
    0.15
    ABEL
    0.15
    cept
    0.14
    ENN
    0.14
    istor
    0.14
    imit
    0.14
     taste
    0.14
    Act Density 0.016%

    No Known Activations