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

    Neuronpedia

    INDEX
    Explanations

    numbers related to quantities or measurements

    oai_token-act-pair · gpt-3.5-turbo

    numbers associated with various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    folk
    -0.84
    âĹ¼
    -0.82
    gets
    -0.74
    holder
    -0.71
    hold
    -0.70
    holders
    -0.69
    Glass
    -0.69
    holding
    -0.68
    flush
    -0.68
     RTX
    -0.67
    POSITIVE LOGITS
    %:
    0.98
    80
    0.92
    90
    0.90
     94
    0.87
    ¢
    0.86
     mph
    0.84
     dB
    0.84
     93
    0.82
     92
    0.81
    803
    0.77
    Act Density 0.033%

    No Known Activations