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

    Neuronpedia

    INDEX
    Explanations

    words expressing certainty or affirmation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rve
    -0.17
    éĥ¡
    -0.16
    _tF
    -0.16
    коп
    -0.15
    cook
    -0.14
    umbn
    -0.14
    ipi
    -0.14
    anca
    -0.14
    aja
    -0.14
    coop
    -0.13
    POSITIVE LOGITS
     be
    0.24
     been
    0.23
    most
    0.20
    sprites
    0.15
    awa
    0.15
    AW
    0.14
    Been
    0.14
    ï¸ı
    0.14
    763
    0.13
     Been
    0.13
    Act Density 0.198%

    No Known Activations