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

    Neuronpedia

    INDEX
    Explanations

    code and function-based assertions and expressions in programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     kasarigan
    -0.77
     nakalista
    -0.73
    IsMutable
    -0.73
    enderror
    -0.71
    interopRequire
    -0.71
    parsedMessage
    -0.69
    AddTagHelper
    -0.69
    WriteTagHelper
    -0.69
     snippetHide
    -0.65
     ModelExpression
    -0.65
    POSITIVE LOGITS
     against
    0.39
     in
    0.39
     around
    0.37
     elsewhere
    0.36
    on
    0.36
     foro
    0.35
     of
    0.35
    лея
    0.34
     from
    0.34
     for
    0.34
    Act Density 1.307%

    No Known Activations