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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "talk" and related phrases about conversation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ỉ
    -0.84
     MacLeod
    -0.82
    டன்
    -0.79
     Bateman
    -0.78
    OrEqualTo
    -0.76
     indeks
    -0.76
    enderror
    -0.74
     Bowden
    -0.74
     Weldon
    -0.74
    Mystery
    -0.73
    POSITIVE LOGITS
     talk
    2.52
    talk
    2.37
     Talk
    2.24
     TALK
    2.21
     talks
    2.17
    Talk
    2.17
     talking
    2.12
     talked
    2.11
    TALK
    1.98
    talking
    1.93
    Act Density 0.040%

    No Known Activations