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

    Neuronpedia

    INDEX
    Explanations

    concepts related to engagement and interaction in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    /from
    -0.17
    offee
    -0.15
    emode
    -0.15
    dez
    -0.14
    (s
    -0.14
    awn
    -0.14
     Bry
    -0.14
    mond
    -0.14
    most
    -0.14
    cks
    -0.14
    POSITIVE LOGITS
    ivate
    0.22
    /respond
    0.18
    eer
    0.18
    chsel
    0.16
    OffsetTable
    0.16
    /testify
    0.16
     cá»Ń
    0.15
    cobra
    0.15
    arken
    0.15
    viso
    0.15
    Act Density 0.278%

    No Known Activations