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

    Neuronpedia

    INDEX
    Explanations

    SQL-like query terms or mathematical expressions

    oai_token-act-pair · gpt-3.5-turbo

    parentheses in mathematical or programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    vell
    -0.83
    atures
    -0.80
    ardless
    -0.77
    ses
    -0.76
    uder
    -0.76
    ionic
    -0.75
    under
    -0.73
    arts
    -0.72
    aton
    -0.71
    duction
    -0.70
    POSITIVE LOGITS
    ;;;;;;;;
    0.79
    ))))
    0.78
    ;;;;;;;;;;;;
    0.77
     ¶
    0.76
    ::::::::
    0.68
    ::::
    0.67
     Colon
    0.66
    ;;;;
    0.65
     {\
    0.63
     srf
    0.62
    Act Density 0.026%

    No Known Activations