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

    Neuronpedia

    INDEX
    Explanations

    references to personal experiences and feelings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    wan
    -0.17
    t
    -0.17
    lite
    -0.15
     dust
    -0.15
    wards
    -0.15
    ongs
    -0.15
    ime
    -0.14
    is
    -0.14
    ÑĢади
    -0.14
    te
    -0.14
    POSITIVE LOGITS
    /us
    0.23
     personally
    0.20
    Schedulers
    0.19
    /Internal
    0.17
    _codegen
    0.17
    /her
    0.17
    @nate
    0.17
    .styleable
    0.16
    #
    0.16
    -même
    0.15
    Act Density 0.044%

    No Known Activations