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

    Neuronpedia

    INDEX
    Explanations

    the word "out" in various contexts

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

    "out"

    np_acts-logits-general · gemini-2.0-flash

    out

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ainfi
    -0.93
     vectorielle
    -0.80
     vectorielles
    -0.72
     fédé
    -0.71
    retudo
    -0.68
     zoude
    -0.68
     plufieurs
    -0.67
     vœ
    -0.66
     quelcon
    -0.66
     avoient
    -0.66
    POSITIVE LOGITS
     out
    1.61
     Out
    1.57
    Out
    1.53
     OUT
    1.47
    out
    1.41
    OUT
    1.23
    EOUT
    1.19
     outs
    1.11
    outs
    1.10
    アウト
    0.94
    Act Density 0.145%

    No Known Activations