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

    Neuronpedia

    INDEX
    Explanations

    modal verbs indicating possibility, ability, or expectation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ê¶Į
    -0.14
    /document
    -0.14
    177
    -0.13
     most
    -0.13
    isia
    -0.13
    .AF
    -0.13
     reap
    -0.13
     trú
    -0.13
    wald
    -0.13
    éĻħ
    -0.13
    POSITIVE LOGITS
    èĪ
    0.16
    ëĶ°
    0.15
    aket
    0.14
     Ding
    0.14
    openh
    0.13
    anders
    0.13
    аÑĤе
    0.13
    för
    0.13
    (EXPR
    0.13
    SWEP
    0.13
    Act Density 0.029%

    No Known Activations