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

    Neuronpedia

    INDEX
    Explanations

    names or identifiers related to individuals

    oai_token-act-pair · gpt-3.5-turbo

    instances of the letter 'r' and various similar phonetic sounds

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     bluff
    -0.61
     curses
    -0.60
     gravel
    -0.59
     finely
    -0.59
     wrink
    -0.58
     comment
    -0.57
    ãĤ¦ãĤ¹
    -0.56
     wound
    -0.56
     merciless
    -0.55
     treacherous
    -0.55
    POSITIVE LOGITS
    aste
    0.94
    ndra
    0.91
    asia
    0.83
    utan
    0.78
    era
    0.78
    arius
    0.77
    uba
    0.76
    ern
    0.76
    raf
    0.76
    uria
    0.75
    Act Density 0.155%

    No Known Activations