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

    Neuronpedia

    INDEX
    Explanations

    references to social impact and assistance programs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orra
    -0.18
    aal
    -0.17
    aso
    -0.17
    orado
    -0.14
    ctions
    -0.14
    ertz
    -0.14
    hetto
    -0.14
     дÑĥ
    -0.14
    รร
    -0.14
    /epl
    -0.14
    POSITIVE LOGITS
    zan
    0.15
    रण
    0.14
    ipa
    0.14
    oline
    0.14
     sur
    0.14
     ske
    0.13
     Southern
    0.13
    oston
    0.13
     magg
    0.13
    ired
    0.13
    Act Density 0.077%

    No Known Activations