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

    Neuronpedia

    INDEX
    Explanations

    descriptions of visual scenes

    oai_token-act-pair · gpt-3.5-turbo

    sentences that end with a period

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    omics
    -0.80
     concede
    -0.71
     equitable
    -0.69
     specifically
    -0.68
    inker
    -0.67
     rescind
    -0.67
    ennes
    -0.66
     correct
    -0.66
    ensor
    -0.66
     detriment
    -0.65
    POSITIVE LOGITS
     Behind
    0.97
     Others
    0.93
     Thick
    0.87
     Dozens
    0.86
     Voices
    0.86
     Occasionally
    0.86
     stares
    0.83
     Across
    0.83
     silhou
    0.82
     Suddenly
    0.82
    Act Density 0.443%

    No Known Activations