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

    Neuronpedia

    INDEX
    Explanations

    references to self-awareness and self-assessment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     joindre
    -0.57
    setArguments
    -0.55
     rangs
    -0.54
     réfrig
    -0.54
    httphttps
    -0.53
     tén
    -0.53
     réus
    -0.53
    expandindo
    -0.53
    YOND
    -0.53
    Sklici
    -0.52
    POSITIVE LOGITS
    MLLoader
    0.58
     nahilalakip
    0.56
     كومونز
    0.56
    lessness
    0.56
     flag
    0.55
     agg
    0.54
     indulgent
    0.53
     depre
    0.53
    flag
    0.53
    same
    0.52
    Act Density 0.122%

    No Known Activations