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

    Neuronpedia

    INDEX
    Explanations

    phrases or sentences starting with the word "generally"

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating commonality or general trends

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÄŁ
    -0.86
     Billion
    -0.76
    hao
    -0.76
    vana
    -0.74
    lda
    -0.73
     Orchestra
    -0.72
    tein
    -0.71
    yle
    -0.71
    ters
    -0.68
    lez
    -0.68
    POSITIVE LOGITS
     regarded
    0.95
     exha
    0.92
     speaking
    0.90
    ensical
    0.85
     assumed
    0.84
     inclined
    0.82
     frowned
    0.82
     metic
    0.81
     confined
    0.81
     accepted
    0.81
    Act Density 0.010%

    No Known Activations