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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating probability or likelihood

    oai_token-act-pair · gpt-3.5-turbo

    phrases expressing likelihood or probability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ciating
    -0.74
    arantine
    -0.73
    perty
    -0.72
    ilan
    -0.70
    GBT
    -0.70
    elight
    -0.70
    nai
    -0.69
    Ô
    -0.68
    rency
    -0.68
    gall
    -0.68
    POSITIVE LOGITS
     that
    1.20
     there
    0.86
     they
    0.85
     THAT
    0.84
    that
    0.75
     whoever
    0.74
     we
    0.72
     none
    0.70
     many
    0.68
     she
    0.68
    Act Density 0.191%

    No Known Activations