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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "talk" and its variations in various contexts, indicating a focus on communication and conversation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     VizieR
    -0.62
     viewType
    -0.61
    νης
    -0.60
     lusso
    -0.59
     uovo
    -0.59
     NgModule
    -0.58
    maal
    -0.58
    ulic
    -0.57
    rdo
    -0.56
     %.
    -0.56
    POSITIVE LOGITS
     conversations
    1.26
     talk
    1.25
     conversation
    1.24
    talk
    1.22
     talking
    1.19
     talked
    1.17
     TALK
    1.15
     talks
    1.12
    talking
    1.12
    Talking
    1.11
    Act Density 0.176%

    No Known Activations