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

    Neuronpedia

    INDEX
    Explanations

    percentage signs followed by numbers

    oai_token-act-pair · gpt-3.5-turbo

    percentage signs and related numerical values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ITED
    -0.77
     compr
    -0.72
     exerc
    -0.71
     reper
    -0.67
     Petersen
    -0.66
     Rav
    -0.64
     scrambled
    -0.61
    ipples
    -0.61
     accomp
    -0.60
    pload
    -0.60
    POSITIVE LOGITS
    %%%%
    0.89
    AppData
    0.80
    rax
    0.74
    ËĪ
    0.74
    rance
    0.72
    imate
    0.72
     ABV
    0.72
    steamapps
    0.71
    esi
    0.71
    FREE
    0.70
    Act Density 0.033%

    No Known Activations