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

    Neuronpedia

    INDEX
    Explanations

    phrases related to expressing concerns

    oai_token-act-pair · gpt-3.5-turbo

    instances of the contraction "don't."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     vulner
    -0.50
     pyramid
    -0.45
     sacrific
    -0.43
     scattering
    -0.42
     Antar
    -0.42
     convenience
    -0.42
     jog
    -0.41
     barr
    -0.41
     surv
    -0.41
     exha
    -0.41
    POSITIVE LOGITS
    ï¸ı
    0.97
    _>
    0.63
    east
    0.62
    âĤ¬
    0.62
    £
    0.61
    ¯
    0.61
    tre
    0.60
    âĻ
    0.60
    $
    0.59
    reci
    0.59
    Act Density 0.528%

    No Known Activations