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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating possibility or uncertainty

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

    expressing possibility

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ValueStyle
    -0.57
     Houſe
    -0.54
    jspx
    -0.54
     houſe
    -0.49
     незавершена
    -0.48
     Efq
    -0.45
    ſelf
    -0.45
     ſp
    -0.44
     estekak
    -0.44
     HasFactory
    -0.42
    POSITIVE LOGITS
     may
    0.94
     might
    0.79
     seems
    0.69
     seem
    0.69
    อาจ
    0.68
    may
    0.65
     talvez
    0.62
     sembler
    0.61
     måske
    0.61
    might
    0.61
    Act Density 0.053%

    No Known Activations