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

    Neuronpedia

    INDEX
    Explanations

    names of specific publications or locations

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific media outlets and publications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rine
    -0.76
    gur
    -0.75
    por
    -0.74
    monary
    -0.74
    aneous
    -0.73
    orius
    -0.71
    oding
    -0.70
    ascript
    -0.70
    ridges
    -0.69
    phrine
    -0.68
    POSITIVE LOGITS
    ship
    0.77
    geist
    0.73
    TextColor
    0.66
    Write
    0.65
    vance
    0.64
    bye
    0.62
    ingly
    0.61
     Rid
    0.61
    ependence
    0.60
    Picture
    0.60
    Act Density 0.149%

    No Known Activations