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

    Neuronpedia

    INDEX
    Explanations

    personal reasons or motivations behind actions or decisions

    oai_token-act-pair · gpt-3.5-turbo

    pronouns associated with a sense of victimization or blame

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Eleven
    -0.66
     Millennium
    -0.65
    ntil
    -0.64
     Towards
    -0.64
    jri
    -0.61
     Around
    -0.61
     Dayton
    -0.60
     Voy
    -0.58
     Opening
    -0.58
     Deg
    -0.58
    POSITIVE LOGITS
     lacked
    1.06
     knew
    1.03
     feared
    1.00
     dared
    0.98
     forgot
    0.97
     couldn
    0.94
     didn
    0.94
     lacks
    0.91
     believe
    0.90
     wanted
    0.90
    Act Density 0.172%

    No Known Activations