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

    Neuronpedia

    INDEX
    Explanations

    words related to product or brand names

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns related to titles, names, and significant terms from various media or products

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ////////////////////////////////
    -0.63
    ãģķ
    -0.61
    ////////
    -0.60
     "'
    -0.58
    acters
    -0.57
     FUN
    -0.56
     JO
    -0.56
     deduction
    -0.56
     compos
    -0.55
     deaf
    -0.55
    POSITIVE LOGITS
    acia
    1.04
    agraph
    1.04
    inct
    1.01
    urion
    1.00
    isphere
    1.00
    inia
    1.00
    acion
    0.99
    onia
    0.99
    rax
    0.98
    endium
    0.97
    Act Density 0.178%

    No Known Activations