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

    Neuronpedia

    INDEX
    Explanations

    single-word captions or labels following the word "Image"

    oai_token-act-pair · gpt-3.5-turbo

    identifiers or labels associated with images or photographs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ually
    -0.63
     nuts
    -0.53
    testing
    -0.52
     Wonderland
    -0.51
    *.
    -0.51
     withdrawals
    -0.51
     unheard
    -0.51
    nia
    -0.50
    TL
    -0.49
     unprepared
    -0.49
    POSITIVE LOGITS
     Caption
    0.83
     ï
    0.71
     OF
    0.70
     of
    0.68
    reenshots
    0.63
     Courtesy
    0.62
    ensor
    0.61
     caption
    0.60
    Courtesy
    0.60
    ourke
    0.60
    Act Density 0.032%

    No Known Activations