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

    Neuronpedia

    INDEX
    Explanations

    dates in the format "Month Day, Year"

    oai_token-act-pair · gpt-3.5-turbo

    specific dates and deadlines

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tumblr
    -0.80
     facets
    -0.80
    urious
    -0.77
    estern
    -0.71
     ponds
    -0.71
    iery
    -0.68
     goats
    -0.64
     grease
    -0.63
    orically
    -0.62
    phia
    -0.61
    POSITIVE LOGITS
     "$:/
    0.71
    taboola
    0.69
    geon
    0.63
    externalActionCode
    0.62
    endment
    0.62
    Female
    0.62
    hu
    0.60
    ledge
    0.60
    chal
    0.60
     Secondary
    0.60
    Act Density 0.199%

    No Known Activations