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

    Neuronpedia

    INDEX
    Explanations

    patterns related to numerical and graphical elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sing
    -0.15
    oute
    -0.15
    ondo
    -0.15
    огод
    -0.15
    ulet
    -0.14
    tsky
    -0.14
     Perf
    -0.14
     loose
    -0.14
    tube
    -0.14
    rial
    -0.14
    POSITIVE LOGITS
    habit
    0.15
    455
    0.15
    γμα
    0.14
     Habit
    0.14
    ayo
    0.13
    ptal
    0.13
     Harm
    0.13
    ainter
    0.13
     bá»ķ
    0.13
    691
    0.13
    Act Density 0.002%

    No Known Activations