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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "talk" and its variations in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    டன்
    -0.84
     MacLeod
    -0.84
     Bateman
    -0.83
     виправивши
    -0.81
    OrEqualTo
    -0.79
    SpringRunner
    -0.78
    enderror
    -0.77
    Ỉ
    -0.76
     leveren
    -0.75
     malen
    -0.75
    POSITIVE LOGITS
     talk
    2.24
    talk
    2.15
     Talk
    2.01
     talks
    1.99
     TALK
    1.98
    Talk
    1.92
     talked
    1.84
    TALK
    1.82
     talking
    1.81
     Talks
    1.77
    Act Density 0.035%

    No Known Activations