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

    Neuronpedia

    INDEX
    Explanations

    numerical values

    oai_token-act-pair · gpt-3.5-turbo

    numerical data, particularly focusing on specific percentages and statistical values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sworth
    -0.88
    gets
    -0.85
    holders
    -0.82
    holder
    -0.81
     Skydragon
    -0.73
    soever
    -0.73
    hold
    -0.71
    folk
    -0.70
    dress
    -0.70
    untu
    -0.70
    POSITIVE LOGITS
    %:
    0.85
    999
    0.85
    odcast
    0.81
    80
    0.79
    ocal
    0.77
     mph
    0.75
    90
    0.75
     kHz
    0.74
     dB
    0.74
    9999
    0.74
    Act Density 0.036%

    No Known Activations