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

    Neuronpedia

    INDEX
    Explanations

    proper nouns or names of individuals

    oai_token-act-pair · gpt-3.5-turbo

    repeated mentions of the name "Lombrozo" in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ĸļ
    -0.67
    ãĥ¯
    -0.63
     preempt
    -0.61
     mould
    -0.61
     compile
    -0.61
     vide
    -0.60
     Guatem
    -0.59
     thumb
    -0.59
     synopsis
    -0.58
     eval
    -0.58
    POSITIVE LOGITS
    aded
    0.83
    ello
    0.81
    uity
    0.80
    udeau
    0.80
    ading
    0.78
    loe
    0.78
    ioxide
    0.76
    agos
    0.76
    acia
    0.76
    ento
    0.74
    Act Density 0.325%

    No Known Activations