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

    Neuronpedia

    INDEX
    Explanations

    words related to conditional or future scenarios

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     resourceCulture
    -0.97
     ddelweddau
    -0.91
    ſelf
    -0.91
    MigrationBuilder
    -0.87
    parsedMessage
    -0.84
    AccessorTable
    -0.84
    bootstrapcdn
    -0.82
     purpoſe
    -0.82
    ſelves
    -0.80
     consultato
    -0.79
    POSITIVE LOGITS
     usually
    0.52
     typically
    0.51
     actually
    0.48
     sometimes
    0.48
    '
    0.46
    stopPropagation
    0.45
    ParseTree
    0.45
    .
    0.45
     
    0.45
    rk
    0.44
    Act Density 0.526%

    No Known Activations