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

    Neuronpedia

    INDEX
    Explanations

    phrases or words indicating extreme negativity or criticism

    oai_token-act-pair · gpt-3.5-turbo

    the word "utter" and its variations to indicate strong emphasis or negative evaluations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pei
    -0.79
    amsung
    -0.79
    apego
    -0.71
    oult
    -0.70
    anwhile
    -0.69
    xual
    -0.67
    aspberry
    -0.67
    OHN
    -0.67
    elled
    -0.67
    abbit
    -0.66
    POSITIVE LOGITS
     utter
    1.14
    ance
    0.84
    ances
    0.83
     uttered
    0.81
     aloud
    0.80
     amaz
    0.80
    TY
    0.76
    ingly
    0.76
    çIJ
    0.73
    nesses
    0.71
    Act Density 0.003%

    No Known Activations