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

    Neuronpedia

    INDEX
    Explanations

    expressions related to critique and evaluation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    adden
    -0.15
    rado
    -0.15
    æĬ¼
    -0.14
     Rou
    -0.14
    avig
    -0.14
    xea
    -0.13
    ocre
    -0.13
    ãĥ³ãĥĶ
    -0.13
    AAAAAAAA
    -0.12
    à¸Ńà¸Ķ
    -0.12
    POSITIVE LOGITS
    第
    0.17
     第
    0.16
    964
    0.15
    999
    0.14
    ulty
    0.14
    61
    0.14
    ote
    0.14
     dalÅ¡ÃŃch
    0.14
     third
    0.13
    401
    0.13
    Act Density 0.074%

    No Known Activations