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

    Neuronpedia

    INDEX
    Explanations

    phrases related to photographs

    oai_token-act-pair · gpt-3.5-turbo

    references to images or photographs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    witch
    -0.73
     Ic
    -0.73
    acs
    -0.72
     intellig
    -0.68
     constructs
    -0.66
    cffff
    -0.66
     lords
    -0.66
     incre
    -0.65
    sett
    -0.65
    abled
    -0.65
    POSITIVE LOGITS
     photo
    3.53
     photograph
    2.74
     photos
    2.65
    photo
    2.48
     Photo
    2.45
     PHOTO
    2.24
     photographs
    2.16
     picture
    2.13
     Photos
    2.11
     photographer
    2.06
    Act Density 0.015%

    No Known Activations