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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the phrase "we are here," indicating support or assistance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eda
    -0.17
    Å¡et
    -0.16
    ango
    -0.15
     sang
    -0.15
    elf
    -0.15
    zes
    -0.14
    rana
    -0.14
    serrat
    -0.14
    VERRIDE
    -0.14
    ARIO
    -0.14
    POSITIVE LOGITS
    eyen
    0.18
    CALL
    0.16
    rapid
    0.15
    IFn
    0.15
    inth
    0.15
     Harmon
    0.14
    haus
    0.14
    LAY
    0.14
    _SHADOW
    0.14
    orman
    0.14
    Act Density 0.020%

    No Known Activations