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

    Neuronpedia

    INDEX
    Explanations

    dates and events represented in a specific format

    oai_token-act-pair · gpt-3.5-turbo

    colons and their associated contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     collateral
    -0.72
    milo
    -0.71
    schild
    -0.68
     manif
    -0.65
    avorite
    -0.65
    wagen
    -0.62
     outwe
    -0.61
     recourse
    -0.61
     disappro
    -0.60
    nesday
    -0.60
    POSITIVE LOGITS
    taboola
    0.78
     SHARES
    0.75
     Spectrum
    0.72
    lement
    0.72
     Provided
    0.72
     Registered
    0.71
    ::::::::
    0.69
     Entered
    0.67
     Cancer
    0.65
     UNIVERS
    0.65
    Act Density 0.028%

    No Known Activations