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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "talk" and related discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    OrEqualTo
    -0.86
    டன்
    -0.85
     виправивши
    -0.78
     MacLeod
    -0.78
    SpringRunner
    -0.77
    Ỉ
    -0.77
     bereiken
    -0.77
     Bateman
    -0.76
     indeks
    -0.76
     malen
    -0.75
    POSITIVE LOGITS
     talk
    1.98
    talk
    1.88
     TALK
    1.78
     Talk
    1.77
     talks
    1.75
    Talk
    1.68
     talking
    1.63
    TALK
    1.60
     talked
    1.60
     Talks
    1.54
    Act Density 0.030%

    No Known Activations