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

    Neuronpedia

    INDEX
    Explanations

    quotes or statements attributed to individuals

    oai_token-act-pair · gpt-3.5-turbo

    mentions of influential individuals or figures in social discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     depreciation
    -0.69
     mathemat
    -0.64
     carp
    -0.63
     darts
    -0.63
     debilitating
    -0.62
     flattened
    -0.62
     sheltered
    -0.61
     manageable
    -0.61
     advantageous
    -0.61
     fancy
    -0.60
    POSITIVE LOGITS
     (@
    1.14
    âĢ
    1.11
    [/
    1.09
    .</
    1.07
     ðŁij
    1.07
    ↵Âł
    1.05
    .#
    1.02
    .<
    1.01
     âľ
    0.99
     âĺ
    0.96
    Act Density 0.535%

    No Known Activations