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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "Talk" and its variations, indicating discussions or conversations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ment
    -0.21
    arily
    -0.18
    orer
    -0.17
    ory
    -0.16
    arity
    -0.16
    ality
    -0.16
    ick
    -0.15
    MENT
    -0.15
    orian
    -0.15
    hof
    -0.15
    POSITIVE LOGITS
    ative
    0.23
    -talk
    0.19
    çŃĴ
    0.18
    ATIVE
    0.17
    walker
    0.17
    SPORT
    0.17
    bubble
    0.17
    shop
    0.16
    rippling
    0.16
     Talk
    0.15
    Act Density 0.035%

    No Known Activations