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

    Neuronpedia

    INDEX
    Explanations

    words related to significance, importance, and role

    oai_token-act-pair · gpt-3.5-turbo

    terms related to authority and significance in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Frey
    -0.77
    ©¶æ
    -0.65
     Ger
    -0.64
    gr
    -0.63
     Dull
    -0.63
     Bus
    -0.62
     Gar
    -0.60
    ker
    -0.60
    ston
    -0.59
    nov
    -0.58
    POSITIVE LOGITS
    iness
    0.80
     usefulness
    0.80
     overseas
    0.75
    iest
    0.75
     predicament
    0.74
     shortcomings
    0.74
     holdings
    0.71
    worthiness
    0.70
     intentions
    0.69
    andestine
    0.69
    Act Density 0.375%

    No Known Activations