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

    Neuronpedia

    INDEX
    Explanations

    future-oriented expressions and modal verbs indicating potential outcomes

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

    followed by "be" or "have"

    np_acts-logits-general · gemini-2.0-flash

    will spur / would be / may have

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ึง
    -0.61
    awtextra
    -0.60
     Efq
    -0.58
    ensioni
    -0.57
    فایل‌لار
    -0.56
    UrlResolution
    -0.54
    amsmath
    -0.51
     dares
    -0.51
     سعی
    -0.51
    */;
    -0.50
    POSITIVE LOGITS
     оригіналу
    0.77
     mean
    0.72
     depend
    0.64
    mean
    0.64
     happen
    0.61
     MEAN
    0.61
     help
    0.60
     involve
    0.60
     '\\;'
    0.59
     save
    0.59
    Act Density 0.270%

    No Known Activations