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

    Neuronpedia

    INDEX
    Explanations

    statements about uncertainty or questioning scenarios

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ########.
    -0.56
    HandlerContext
    -0.52
    chanel
    -0.48
    VIAF
    -0.48
     esternos
    -0.45
    addCriterion
    -0.43
    ⤒
    -0.42
    InjectAttribute
    -0.42
     Grat
    -0.42
     geschiedenis
    -0.42
    POSITIVE LOGITS
    嘛
    0.48
     chance
    0.44
    反正
    0.40
    毕竟
    0.38
     hopefully
    0.38
     Hopefully
    0.38
     Schließlich
    0.37
    Hopefully
    0.36
    ContentLoaded
    0.36
    ņas
    0.35
    Act Density 0.336%

    No Known Activations