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

    Neuronpedia

    INDEX
    Explanations

    keywords that indicate capability, process, or conditions related to actions and states

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    agra
    -0.15
    ote
    -0.15
    ango
    -0.14
    copyright
    -0.14
    ãĥĢãĤ¤
    -0.14
     s
    -0.14
     copy
    -0.14
    oga
    -0.14
    empo
    -0.14
    erton
    -0.14
    POSITIVE LOGITS
    aspers
    0.17
    ARSE
    0.16
    uci
    0.15
    ëŀ
    0.15
    acl
    0.15
    olie
    0.15
    .hom
    0.15
    amik
    0.15
    åį
    0.14
    ieber
    0.14
    Act Density 0.002%

    No Known Activations