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

    Neuronpedia

    INDEX
    Explanations

    modal verbs indicating ability or possibility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Noir
    -0.15
    oeff
    -0.14
    tit
    -0.14
    наÑĩе
    -0.14
    ocado
    -0.14
    ocs
    -0.14
    odi
    -0.14
    odic
    -0.14
    odie
    -0.13
    aka
    -0.13
    POSITIVE LOGITS
    WithOptions
    0.17
    deaux
    0.15
    ifo
    0.15
     Voll
    0.15
    chter
    0.15
    lom
    0.14
    Ļ¨
    0.14
    WithType
    0.14
    ameron
    0.14
    íĥĿ
    0.14
    Act Density 0.032%

    No Known Activations