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

    Neuronpedia

    INDEX
    Explanations

    negative sentiments and expressions of disappointment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     alternate
    -0.15
    ä¾
    -0.14
    ves
    -0.14
    gh
    -0.14
    ao
    -0.14
    ORM
    -0.14
     cab
    -0.14
    .Butter
    -0.14
    heels
    -0.13
    verted
    -0.13
    POSITIVE LOGITS
    iros
    0.16
     Sampler
    0.15
    erosis
    0.15
    é¼»
    0.14
    GPC
    0.14
    _logging
    0.14
    overall
    0.14
    elle
    0.14
    .online
    0.13
    ıb
    0.13
    Act Density 0.096%

    No Known Activations