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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate authorship or agency

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    erdale
    -0.15
    ulti
    -0.15
    shal
    -0.15
    Ø´ÙĬ
    -0.15
    adil
    -0.15
    kad
    -0.14
    odega
    -0.14
    BuilderFactory
    -0.14
    rok
    -0.14
    uhan
    -0.14
    POSITIVE LOGITS
     us
    0.20
     means
    0.19
     accident
    0.17
     experienced
    0.16
    laws
    0.16
     ab
    0.15
    lined
    0.15
     way
    0.15
     Nature
    0.14
    products
    0.14
    Act Density 0.148%

    No Known Activations