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

    Neuronpedia

    INDEX
    Explanations

    images or photographs mentioned in text descriptions

    oai_token-act-pair · gpt-3.5-turbo

    instances of individuals or groups in visual contexts or photographs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     accordingly
    -0.66
    conom
    -0.66
     insure
    -0.65
    etheless
    -0.65
     Ratings
    -0.65
    æ©Ł
    -0.65
    volent
    -0.64
    ologies
    -0.63
     limits
    -0.62
     guarantees
    -0.62
    POSITIVE LOGITS
     perched
    0.79
     surrounded
    0.77
     kneeling
    0.75
     flanked
    0.73
     smiling
    0.73
     nude
    0.72
    asma
    0.72
     handcuffed
    0.71
     selfie
    0.68
     blinking
    0.68
    Act Density 0.622%

    No Known Activations