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

    Neuronpedia

    INDEX
    Explanations

    linguistic features related to social and cultural contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ainen
    -0.18
    ocaly
    -0.15
    arsers
    -0.15
    aste
    -0.15
     Amp
    -0.15
    mans
    -0.15
    ikut
    -0.14
    aN
    -0.14
    ¢
    -0.14
    ãĥ³
    -0.14
    POSITIVE LOGITS
     Morr
    0.20
    semi
    0.17
    ug
    0.16
    ört
    0.15
    borg
    0.14
    glich
    0.14
    ÄĻki
    0.14
    incinn
    0.14
    ultz
    0.14
    ãĤ±ãĥĥãĥĪ
    0.14
    Act Density 0.051%

    No Known Activations