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

    Neuronpedia

    INDEX
    Explanations

    topics related to community incidents and social issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pard
    -0.15
    lÃŃ
    -0.13
     dames
    -0.13
    /the
    -0.13
    bish
    -0.13
     autos
    -0.12
    æĺ¯ä¸Ģ个
    -0.12
    ìħĺ
    -0.12
     ÅĻÃŃj
    -0.12
    cki
    -0.12
    POSITIVE LOGITS
    anja
    0.17
     same
    0.15
     entire
    0.15
    oenix
    0.15
    sert
    0.14
    oload
    0.14
     latest
    0.13
    addtogroup
    0.13
    semble
    0.13
    chos
    0.13
    Act Density 0.527%

    No Known Activations