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

    Neuronpedia

    INDEX
    Explanations

    phrases related to manual actions or processes

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

    performing actions manually

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    jsxFileName
    -0.34
    ถม
    -0.31
     skydd
    -0.31
    zelfde
    -0.31
     useStyles
    -0.31
    游戏亮点
    -0.28
     выпуск
    -0.27
     country
    -0.27
     puissance
    -0.27
     hizmet
    -0.27
    POSITIVE LOGITS
     manually
    0.92
     manualmente
    0.84
     Manually
    0.82
    Manually
    0.81
    manual
    0.78
     manual
    0.70
    errHandler
    0.70
    Manual
    0.69
    EDEFAULT
    0.69
    IVEREF
    0.68
    Act Density 0.027%

    No Known Activations