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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "talk" in various contexts and forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    icari
    -0.15
    hw
    -0.15
    ÅĻev
    -0.14
    enschaft
    -0.14
    hall
    -0.14
    cci
    -0.14
    halb
    -0.14
    Ú¯ÙĬ
    -0.13
    물
    -0.13
    icot
    -0.13
    POSITIVE LOGITS
    -about
    0.18
     about
    0.18
    tract
    0.18
    ative
    0.17
    SPORT
    0.16
    ackage
    0.16
    incare
    0.15
    about
    0.15
    onn
    0.15
    oring
    0.15
    Act Density 0.037%

    No Known Activations