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

    Neuronpedia

    INDEX
    Explanations

    future tense verbs indicating intention or expectation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    isu
    -0.15
    emas
    -0.14
    onavir
    -0.14
    umat
    -0.14
    y
    -0.14
    evice
    -0.14
    ži
    -0.14
    icket
    -0.14
    pute
    -0.14
    AXB
    -0.14
    POSITIVE LOGITS
    -ton
    0.15
    ampp
    0.15
    _HI
    0.14
    .inline
    0.13
    rych
    0.13
    ık
    0.13
    HI
    0.13
    ÑģÑı
    0.13
    boa
    0.13
    ogg
    0.13
    Act Density 0.079%

    No Known Activations