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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "interact" and its variations in contexts related to engagement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iyet
    -0.17
    ego
    -0.17
    ç¼ĺ
    -0.16
    itoris
    -0.15
    /tiny
    -0.15
    enco
    -0.15
    readcr
    -0.14
    Ù
    -0.14
    chester
    -0.14
     ActionTypes
    -0.14
    POSITIVE LOGITS
    uality
    0.21
    UAL
    0.19
    ual
    0.19
    ivate
    0.17
    al
    0.17
    uating
    0.17
    ively
    0.16
    ed
    0.16
    ype
    0.16
    nel
    0.15
    Act Density 0.031%

    No Known Activations