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

    Neuronpedia

    INDEX
    Explanations

    phrases related to vision or viewpoints

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to visual perception or attention

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    alli
    -0.73
    hement
    -0.70
    iatus
    -0.70
    States
    -0.66
     Tradable
    -0.65
    fml
    -0.65
    anwhile
    -0.64
    iances
    -0.64
    ecause
    -0.63
    gress
    -0.63
    POSITIVE LOGITS
     palate
    0.81
     ears
    0.80
    ĸļ
    0.78
     piercing
    0.73
     deaf
    0.72
     sucker
    0.71
     Canaver
    0.71
     migraine
    0.68
     bleed
    0.67
     watering
    0.65
    Act Density 0.434%

    No Known Activations