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

    Neuronpedia

    INDEX
    Explanations

    terms indicating widespread prevalence or commonality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    issen
    -0.18
    chten
    -0.17
    imore
    -0.16
    addtogroup
    -0.16
    rack
    -0.15
    tir
    -0.15
    htar
    -0.15
    eu
    -0.14
    luk
    -0.14
    thouse
    -0.14
    POSITIVE LOGITS
    als
    0.19
     Fountain
    0.15
    кав
    0.15
    dale
    0.15
    unic
    0.14
     Inch
    0.14
    ìĦŃ
    0.14
    nal
    0.14
    ÑĢиÑı
    0.14
    rib
    0.14
    Act Density 0.005%

    No Known Activations