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

    Neuronpedia

    INDEX
    Explanations

    names or words related to a particular place or concept, potentially related to continents or people's names

    oai_token-act-pair · gpt-3.5-turbo

    the occurrences of the substring "ond" within words

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ======
    -0.89
    mson
    -0.87
    ãĤµ
    -0.84
    kson
    -0.77
    jriwal
    -0.75
    ttle
    -0.73
    ãĥ³ãĤ¸
    -0.69
    ãĥīãĥ©ãĤ´ãĥ³
    -0.68
    veyard
    -0.66
    CLE
    -0.66
    POSITIVE LOGITS
    ragon
    1.01
    orf
    0.91
    erer
    0.91
    ering
    0.90
    irect
    0.88
    isl
    0.87
    ocument
    0.86
    iverse
    0.86
    itional
    0.85
    etermin
    0.85
    Act Density 0.023%

    No Known Activations