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

    Neuronpedia

    INDEX
    Explanations

    numeric identifiers within text

    oai_token-act-pair · gpt-3.5-turbo

    references to events, particularly those related to mourning or tributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Sword
    -0.77
    ————————————————
    -0.76
    Reviewed
    -0.73
    DR
    -0.68
    GD
    -0.67
    Score
    -0.65
    Apart
    -0.63
    Frag
    -0.63
     Unlimited
    -0.63
    Regular
    -0.61
    POSITIVE LOGITS
     Photos
    0.84
     Caption
    0.81
    ideshow
    0.77
     photographed
    0.73
     FILE
    0.72
     REUTERS
    0.69
     sparking
    0.69
     poses
    0.68
     photograp
    0.68
     rescue
    0.66
    Act Density 0.109%

    No Known Activations