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

    Neuronpedia

    INDEX
    Explanations

    statements indicating knowledge or awareness of a situation or action

    oai_token-act-pair · gpt-3.5-turbo

    references to knowledge and awareness in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     suggestion
    -0.77
     reluct
    -0.71
    wik
    -0.69
    edia
    -0.66
     insistence
    -0.65
     understandably
    -0.64
     recommends
    -0.64
    ioch
    -0.63
    ertodd
    -0.63
     Feast
    -0.62
    POSITIVE LOGITS
     outnumbered
    0.77
     wasting
    0.75
     tread
    0.72
     kindred
    0.72
     belong
    0.71
     invincible
    0.71
     done
    0.68
    done
    0.67
     owed
    0.67
     witnessing
    0.65
    Act Density 0.301%

    No Known Activations