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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "out" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    work out

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    pośred
    -0.37
     inmediato
    -0.34
     ciertamente
    -0.30
     cucharadita
    -0.29
     británico
    -0.28
     UK
    -0.25
     británica
    -0.25
     britannique
    -0.24
     lluvias
    -0.23
     plomo
    -0.23
    POSITIVE LOGITS
     Geiſt
    0.75
    EndContext
    0.75
     snippetHide
    0.69
    IntoConstraints
    0.69
     geſch
    0.68
    fastjson
    0.66
    WriteBarrier
    0.66
    ↆ
    0.66
     ſeyn
    0.66
    ValueStyle
    0.66
    Act Density 0.117%

    No Known Activations