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

    Neuronpedia

    INDEX
    Explanations

    mentions of specific organizations or entities within a particular context or scenario

    oai_token-act-pair · gpt-3.5-turbo

    the presence of opening parentheses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iazep
    -0.75
    irds
    -0.74
     entitle
    -0.71
     lull
    -0.71
     everyday
    -0.68
    quished
    -0.68
    olicy
    -0.66
     pale
    -0.64
    uly
    -0.64
     nightly
    -0.63
    POSITIVE LOGITS
    emphasis
    1.20
    sic
    1.15
    see
    1.10
    including
    1.06
    formerly
    1.05
    ...)
    1.05
    excluding
    1.01
    also
    1.01
    via
    1.00
    which
    0.98
    Act Density 0.204%

    No Known Activations