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

    Neuronpedia

    INDEX
    Explanations

    actions or statements made by important political figures

    oai_token-act-pair · gpt-3.5-turbo

    verbs associated with making or delivering statements and offers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    \.
    -0.79
    usercontent
    -0.74
    lords
    -0.71
    abiding
    -0.70
    cause
    -0.69
    LINE
    -0.66
    oin
    -0.65
    âĨij
    -0.65
     [];
    -0.64
    selves
    -0.63
    POSITIVE LOGITS
     himself
    1.22
     his
    1.20
     remarks
    1.00
     keynote
    0.86
     scathing
    0.84
     Himself
    0.82
     congratulations
    0.80
     praise
    0.78
     condolences
    0.78
     fiery
    0.77
    Act Density 0.291%

    No Known Activations