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

    Neuronpedia

    INDEX
    Explanations

    proper nouns or names mentioned in text

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to names

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    fulness
    -0.79
    iasm
    -0.72
    oday
    -0.68
    entimes
    -0.67
    pour
    -0.65
    fully
    -0.65
    going
    -0.63
    athy
    -0.62
    iment
    -0.62
     touch
    -0.62
    POSITIVE LOGITS
     culprit
    0.98
     antagonist
    0.68
     protagonist
    0.68
     Killer
    0.68
     suspects
    0.67
     forthcoming
    0.66
     supplier
    0.66
     publisher
    0.65
     successor
    0.65
     perpetrator
    0.64
    Act Density 0.163%

    No Known Activations