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

    Neuronpedia

    INDEX
    Explanations

    phrases related to superficial or initial impressions

    oai_token-act-pair · gpt-3.5-turbo

    references to appearances or superficial characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    icer
    -0.79
    ashington
    -0.69
    rench
    -0.68
    tailed
    -0.66
     quar
    -0.65
    ãĥĺ
    -0.65
    rus
    -0.65
    Joined
    -0.64
    die
    -0.60
    cel
    -0.60
    POSITIVE LOGITS
     glance
    1.18
     blush
    0.81
     superf
    0.70
    pedia
    0.69
     resemb
    0.68
     sounds
    0.66
     LOOK
    0.66
     standpoint
    0.65
     clues
    0.65
     superficial
    0.65
    Act Density 0.111%

    No Known Activations