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

    Neuronpedia

    INDEX
    Explanations

    titles of popular dystopian films and related works

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arra
    -0.17
    åº
    -0.15
    aja
    -0.15
    etro
    -0.15
    ara
    -0.14
    IRO
    -0.14
    stro
    -0.14
    oger
    -0.14
     Coverage
    -0.13
    ento
    -0.13
    POSITIVE LOGITS
    çħ§
    0.14
     overload
    0.14
    dal
    0.13
    emez
    0.13
     absentee
    0.13
    wers
    0.13
     Bulk
    0.13
    826
    0.13
    naz
    0.13
    alsy
    0.13
    Act Density 0.059%

    No Known Activations