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

    Neuronpedia

    INDEX
    Explanations

    mention of superficial appearances or first impressions

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate a superficial assessment or first impression of something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    icer
    -0.78
    rench
    -0.71
    die
    -0.69
    ammy
    -0.67
    rus
    -0.67
    este
    -0.65
    ashington
    -0.63
    tailed
    -0.62
    anwhile
    -0.60
    govtrack
    -0.59
    POSITIVE LOGITS
     glance
    1.07
     blush
    0.77
     resemb
    0.68
    ãħĭ
    0.65
     it
    0.63
     superf
    0.63
     looks
    0.62
     LOOK
    0.61
     illusions
    0.61
     Aren
    0.61
    Act Density 0.130%

    No Known Activations