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

    Neuronpedia

    INDEX
    Explanations

    assertions of certainty and confidence in opinions or statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    INTR
    -0.19
    uw
    -0.16
    ucken
    -0.15
     reportedly
    -0.14
     seems
    -0.14
    imen
    -0.14
    ì°Į
    -0.14
    idUser
    -0.14
    iska
    -0.14
     recap
    -0.14
    POSITIVE LOGITS
     countless
    0.15
     alguna
    0.14
    allet
    0.14
     similarly
    0.14
     many
    0.14
    éŃĤ
    0.14
    ÑĢоÑĩ
    0.14
     somewhere
    0.13
    gesch
    0.13
    pector
    0.13
    Act Density 0.165%

    No Known Activations