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

    Neuronpedia

    INDEX
    Explanations

    expressions of improvement and resistance in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rance
    -0.16
    arto
    -0.15
    .modules
    -0.14
    igsaw
    -0.14
    UILT
    -0.13
    istr
    -0.13
    ichel
    -0.13
    ilton
    -0.13
    rab
    -0.13
    WARD
    -0.13
    POSITIVE LOGITS
    DRV
    0.15
    itto
    0.15
    ivre
    0.14
    usra
    0.14
    asurement
    0.14
    биÑĤ
    0.14
    adaki
    0.14
    ypi
    0.14
    weed
    0.14
    ccak
    0.14
    Act Density 0.335%

    No Known Activations