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

    Neuronpedia

    INDEX
    Explanations

    references to close-up views or perspectives

    oai_token-act-pair · gpt-3.5-turbo

    references to close-up perspectives or images

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     administ
    -0.71
     horm
    -0.70
    agara
    -0.68
    lain
    -0.66
     ransom
    -0.66
    VILLE
    -0.64
    oub
    -0.63
    soType
    -0.62
     regist
    -0.62
     delinqu
    -0.61
    POSITIVE LOGITS
    shots
    0.97
    shot
    0.90
     photographs
    0.79
     drawings
    0.70
    arching
    0.70
    camera
    0.70
    ooter
    0.69
    loader
    0.69
    reenshot
    0.69
    ography
    0.69
    Act Density 0.071%

    No Known Activations