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

    Neuronpedia

    INDEX
    Explanations

    names related to individuals

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, particularly names of people and teams

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     tremend
    -0.88
     conclud
    -0.80
    ©¶æ
    -0.79
    Þ
    -0.78
     Operation
    -0.77
     exting
    -0.75
     Orn
    -0.74
     acknow
    -0.74
     Paran
    -0.74
     comr
    -0.73
    POSITIVE LOGITS
    eret
    0.86
    iggs
    0.85
    inson
    0.85
    inho
    0.84
    essel
    0.84
    iesta
    0.79
    ijah
    0.77
    oise
    0.77
    aldi
    0.76
    achev
    0.75
    Act Density 0.171%

    No Known Activations