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

    Neuronpedia

    INDEX
    Explanations

    terms related to health and safety practices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ahir
    -0.16
    icolor
    -0.16
    reur
    -0.14
     Misc
    -0.14
    #af
    -0.14
    hek
    -0.14
    anca
    -0.14
    TEGER
    -0.13
    reasonable
    -0.13
    à¸ģารส
    -0.13
    POSITIVE LOGITS
    §
    0.16
     bid
    0.14
     usually
    0.14
    ayah
    0.14
     skate
    0.14
    entifier
    0.13
    BX
    0.13
    buzz
    0.13
    sha
    0.13
    ku
    0.13
    Act Density 0.218%

    No Known Activations