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

    Neuronpedia

    INDEX
    Explanations

    specific keywords or phrases indicating significant actions, objects, or concepts within various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    amma
    -0.15
    á»ĩn
    -0.14
    aug
    -0.14
    uido
    -0.14
    Ïħγ
    -0.14
    omba
    -0.14
     ag
    -0.14
    RCT
    -0.13
    oldem
    -0.13
    girls
    -0.13
    POSITIVE LOGITS
     Hip
    0.15
    ois
    0.15
     Firm
    0.15
    .btnExit
    0.14
     Sherman
    0.14
    inst
    0.14
    elon
    0.14
    sg
    0.14
     Twe
    0.14
    _PT
    0.14
    Act Density 0.008%

    No Known Activations