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

    Neuronpedia

    INDEX
    Explanations

    the word "all" occuring before a number

    oai_token-act-pair · gpt-3.5-turbo

    phrases that emphasize the concept of "all" or totality in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    yip
    -0.63
     precip
    -0.61
    yi
    -0.61
    nell
    -0.60
    xit
    -0.59
     horizon
    -0.59
    illac
    -0.58
    velt
    -0.57
    inates
    -0.57
    istant
    -0.56
    POSITIVE LOGITS
     sorts
    0.86
    ocating
    0.86
     kinds
    0.84
    iances
    0.78
    CLASSIFIED
    0.76
    usions
    0.75
    edged
    0.74
    igator
    0.73
    OWER
    0.72
    uv
    0.70
    Act Density 0.067%

    No Known Activations