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

    Neuronpedia

    INDEX
    Explanations

    phrases enclosed in quotation marks

    oai_token-act-pair · gpt-3.5-turbo

    quotes and dialogue within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     administrators
    -0.81
     editing
    -0.77
     Archdemon
    -0.76
     Blacks
    -0.76
     IDs
    -0.75
     elements
    -0.75
     ups
    -0.75
     exits
    -0.75
     ov
    -0.74
     addresses
    -0.74
    POSITIVE LOGITS
    few
    1.32
    very
    1.31
    huge
    1.25
    classic
    1.25
    little
    1.23
    reasonable
    1.21
    significant
    1.20
    special
    1.19
    highly
    1.19
    virtual
    1.18
    Act Density 0.051%

    No Known Activations