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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate companionship or support in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .yy
    -0.17
    tees
    -0.16
    ean
    -0.14
    erville
    -0.14
    rows
    -0.14
    owski
    -0.14
    ÏģÏī
    -0.14
    athlon
    -0.14
    å±Ĭ
    -0.13
    .decorate
    -0.13
    POSITIVE LOGITS
    avis
    0.15
    onomy
    0.15
     Robbins
    0.15
     tep
    0.14
    alsa
    0.14
    atron
    0.14
    onian
    0.14
    clave
    0.14
    CTX
    0.14
    à¥Įत
    0.13
    Act Density 0.302%

    No Known Activations