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

    Neuronpedia

    INDEX
    Explanations

    adjectives or adverbs expressing extremeness or definitiveness

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating difficulty, impossibility, or elusiveness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    doms
    -0.76
    ults
    -0.73
    ilers
    -0.72
    enaries
    -0.72
    sheets
    -0.69
     confronts
    -0.68
     backs
    -0.68
     throats
    -0.68
     clears
    -0.67
     wills
    -0.67
    POSITIVE LOGITS
     TBD
    0.86
     unlikely
    0.83
    omorph
    0.77
     tricky
    0.77
     fascinating
    0.76
     synonymous
    0.74
     rife
    0.74
     dependent
    0.74
     obvious
    0.73
     rare
    0.72
    Act Density 0.507%

    No Known Activations