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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "talk" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ment
    -0.18
    arily
    -0.17
    ional
    -0.17
    orer
    -0.16
    ijke
    -0.15
    etroit
    -0.15
    _msgs
    -0.15
    unk
    -0.15
    MENT
    -0.15
    ory
    -0.14
    POSITIVE LOGITS
    ative
    0.28
    SPORT
    0.21
    ATIVE
    0.20
    -talk
    0.18
    bubble
    0.18
    çŃĴ
    0.17
    870
    0.17
     about
    0.17
    -shop
    0.17
    shop
    0.16
    Act Density 0.032%

    No Known Activations