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

    Neuronpedia

    INDEX
    Explanations

    underscores and underscores followed by numbers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    s
    -0.25
    Ùĩ
    -0.19
    h
    -0.18
    in
    -0.17
    aphore
    -0.17
    ERNEL
    -0.17
    eneric
    -0.16
    t
    -0.16
     latter
    -0.16
    f
    -0.15
    POSITIVE LOGITS
    ever
    0.19
    taboola
    0.15
    &_
    0.15
    ioxide
    0.14
    flen
    0.14
    deen
    0.14
    jspx
    0.14
    اسطة
    0.14
    etch
    0.14
    rollers
    0.14
    Act Density 0.060%

    No Known Activations