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

    Neuronpedia

    INDEX
    Explanations

    phrases emphasizing extreme negativity or finality

    oai_token-act-pair · gpt-3.5-turbo

    the word "utter" and its variations, indicating expressions of emphasis or strong statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    actionDate
    -0.82
    OHN
    -0.75
    llah
    -0.73
    amsung
    -0.73
    xual
    -0.71
     Feder
    -0.66
    ACP
    -0.65
    externalActionCode
    -0.64
     Organizations
    -0.63
    Æ
    -0.62
    POSITIVE LOGITS
    ances
    1.19
    ance
    1.09
    most
    0.94
    aneous
    0.84
     amaz
    0.80
    aneously
    0.77
    ness
    0.76
    opard
    0.74
    TY
    0.74
    itarian
    0.74
    Act Density 0.029%

    No Known Activations