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

    Neuronpedia

    INDEX
    Explanations

    contractions ('aren't', 'won't', 'isn't', etc.)

    oai_token-act-pair · gpt-3.5-turbo

    negations or contractions related to the state of being

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anwhile
    -0.86
     enthusi
    -0.83
     destro
    -0.78
     princ
    -0.78
     eleph
    -0.76
     gobl
    -0.76
     newcom
    -0.74
     unnecess
    -0.69
     exha
    -0.69
     metic
    -0.68
    POSITIVE LOGITS
    't
    1.73
    ited
    0.88
    ÃŃ
    0.88
    ´
    0.87
    iting
    0.86
    itely
    0.85
    atically
    0.83
    Dispatch
    0.80
    uts
    0.79
    acio
    0.79
    Act Density 0.082%

    No Known Activations