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

    Neuronpedia

    INDEX
    Explanations

    conditional phrases that indicate variability or dependence on certain factors

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

    "Depending on"

    np_acts-logits-general · gemini-2.0-flash

    depending on how or whether

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    merking
    -0.52
    Pty
    -0.51
    textwidth
    -0.49
    bladet
    -0.48
    •••
    -0.48
    ?>
    -0.47
    ylus
    -0.46
    ->___
    -0.46
    abinieri
    -0.46
    достатки
    -0.46
    POSITIVE LOGITS
     depending
    1.15
    depending
    1.03
     how
    0.98
     depends
    0.91
    Depending
    0.89
     Depending
    0.89
     whether
    0.86
    Depends
    0.85
    RectangleBorder
    0.82
    depends
    0.80
    Act Density 0.098%

    No Known Activations