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

    Neuronpedia

    INDEX
    Explanations

    connections and patterns in text related to questioning and classification

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eter
    -0.18
    leur
    -0.16
    ÃŃg
    -0.15
    atal
    -0.14
    evi
    -0.14
    vic
    -0.14
    оÑĢож
    -0.14
     каÑģ
    -0.14
    atica
    -0.14
    cient
    -0.14
    POSITIVE LOGITS
    iyas
    0.15
     hor
    0.15
    anyak
    0.15
    ameleon
    0.15
    adar
    0.14
    .vn
    0.14
     Goose
    0.14
     porr
    0.13
     Moody
    0.13
    istrovstvÃŃ
    0.13
    Act Density 0.029%

    No Known Activations