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

    Neuronpedia

    INDEX
    Explanations

    actions or intentions described with verbs in the form "to do [something]"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "will do" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lights
    -0.69
    ONSORED
    -0.65
    dayName
    -0.65
    hog
    -0.64
    uses
    -0.63
    mares
    -0.62
    pac
    -0.59
    ulative
    -0.58
    ricted
    -0.58
    liner
    -0.58
    POSITIVE LOGITS
    ppel
    0.95
    lez
    0.91
    omsday
    0.88
    vet
    0.86
    ozy
    0.85
    oms
    0.82
    omething
    0.80
    pez
    0.79
     nothing
    0.76
    le
    0.75
    Act Density 0.109%

    No Known Activations