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

    Neuronpedia

    INDEX
    Explanations

    words related to certainty and possibility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    _tF
    -0.15
    annis
    -0.15
    rve
    -0.14
    umbn
    -0.14
    éĥ¡
    -0.14
    coop
    -0.14
    enant
    -0.14
     Interracial
    -0.14
    entials
    -0.13
     напÑĢи
    -0.13
    POSITIVE LOGITS
     be
    0.25
     been
    0.25
    most
    0.18
     downt
    0.15
    awa
    0.14
    ï¸ı
    0.14
    umo
    0.14
    /csv
    0.14
    owski
    0.14
    been
    0.14
    Act Density 0.259%

    No Known Activations