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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating comparison or contrast

    oai_token-act-pair · gpt-3.5-turbo

    phrases expressing different perspectives or interpretations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     UCH
    -0.72
    andel
    -0.68
     grade
    -0.65
    gur
    -0.63
    iere
    -0.63
    ilage
    -0.63
    aquin
    -0.61
    aeus
    -0.61
    erm
    -0.60
    prus
    -0.60
    POSITIVE LOGITS
     resembles
    0.87
     resemble
    0.69
     resembled
    0.69
     stranger
    0.69
     resemb
    0.68
     parallels
    0.65
    hift
    0.64
     Lange
    0.64
     perverse
    0.62
     analogous
    0.62
    Act Density 0.042%

    No Known Activations