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

    Neuronpedia

    INDEX
    Explanations

    references to the English language or its representation in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    start of user turn

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     StringTokenizer
    -0.57
     pleaſure
    -0.54
     houſe
    -0.54
     myſelf
    -0.52
    IMPORTED
    -0.52
    insatz
    -0.52
     ſch
    -0.51
     gräns
    -0.50
    anyahu
    -0.50
     miniaturka
    -0.50
    POSITIVE LOGITS
    s
    0.51
    rs
    0.48
    لينكات
    0.43
    BS
    0.43
    AS
    0.43
    riks
    0.43
     Gre
    0.42
    .
    0.41
    mas
    0.41
    Trama
    0.40
    Act Density 0.000%

    No Known Activations