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

    Neuronpedia

    INDEX
    Explanations

    elements of dramatic conflict and high-stakes situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lobals
    -0.15
    uky
    -0.15
    imizer
    -0.15
    .xmlbeans
    -0.14
    asper
    -0.14
    abei
    -0.14
    stor
    -0.14
    ersist
    -0.13
     gratuit
    -0.13
    arehouse
    -0.13
    POSITIVE LOGITS
     secrets
    0.17
    ù
    0.16
     danger
    0.16
     darkest
    0.16
     jeopard
    0.15
     dangerous
    0.15
     dred
    0.15
     past
    0.14
     secret
    0.14
    proof
    0.14
    Act Density 0.361%

    No Known Activations