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

    Neuronpedia

    INDEX
    Explanations

    mentions of the word "bespoke"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "bes" or its variations in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Reviewer
    -0.83
    ãĥ¼ãĥĨ
    -0.81
    ITION
    -0.75
    OPLE
    -0.74
    ALLY
    -0.73
     Executive
    -0.66
    istically
    -0.65
     Sawyer
    -0.63
     atmosphere
    -0.61
     McH
    -0.61
    POSITIVE LOGITS
    erker
    1.06
    sembly
    1.04
    iege
    0.98
    pect
    0.96
    hov
    0.95
    aved
    0.93
    heng
    0.92
    cape
    0.89
    es
    0.88
    pread
    0.86
    Act Density 0.030%

    No Known Activations