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

    Neuronpedia

    INDEX
    Explanations

    modal verbs indicating possibility or ability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    annis
    -0.18
    arb
    -0.15
    ivre
    -0.14
    ifu
    -0.14
    roperty
    -0.14
    raya
    -0.14
    smarty
    -0.14
    grese
    -0.14
    919
    -0.13
     Kop
    -0.13
    POSITIVE LOGITS
    icut
    0.15
    ãģªãĤĭ
    0.14
     dildo
    0.14
    νÏĦ
    0.14
    ült
    0.13
     znal
    0.13
    _PAIR
    0.13
    iali
    0.13
     infix
    0.13
     Wah
    0.13
    Act Density 0.096%

    No Known Activations