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

    Neuronpedia

    INDEX
    Explanations

    references to flight and flying mechanisms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     resposta
    -0.52
     peores
    -0.43
     Roskov
    -0.43
     préalable
    -0.41
     harten
    -0.40
     andern
    -0.40
     tiefe
    -0.39
     prevenção
    -0.39
     ocasião
    -0.39
     محت
    -0.38
    POSITIVE LOGITS
     flying
    1.33
    Fly
    1.33
     Fly
    1.31
     fly
    1.31
     FLY
    1.30
     flown
    1.29
    Flying
    1.27
     Flying
    1.24
    flying
    1.20
     flew
    1.20
    Act Density 0.120%

    No Known Activations