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

    Neuronpedia

    INDEX
    Explanations

    mathematical operations or code-related snippets

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of mathematical or numerical expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    soDeliveryDate
    -0.74
     Grimes
    -0.72
    opathic
    -0.70
     Nare
    -0.65
     Owens
    -0.65
    meyer
    -0.64
     Reloaded
    -0.64
    zb
    -0.64
     Lauder
    -0.63
    zel
    -0.62
    POSITIVE LOGITS
    -+-+-+-+
    1.21
    ++++++++++++++++
    1.17
    /+
    1.12
    -+
    1.00
    ++++
    0.97
    /-
    0.94
    --+
    0.88
    ++++++++
    0.86
    âĢ¢âĢ¢
    0.71
    union
    0.69
    Act Density 0.021%

    No Known Activations