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

    Neuronpedia

    INDEX
    Explanations

    phrases related to possibilities and conditions in various contexts

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

    possibility or frequency

    np_acts-logits-general · gemini-2.0-flash

    likelihood, possibility, and frequency

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Erişim
    -0.48
    <eos>
    -0.45
     ball
    -0.44
    andal
    -0.43
    óta
    -0.41
     ax
    -0.41
    ons
    -0.41
    лись
    -0.41
    એ
    -0.40
    ושה
    -0.40
    POSITIVE LOGITS
     mungkin
    1.05
    likely
    0.98
     likely
    0.97
     may
    0.89
    Likely
    0.88
     probably
    0.88
    probably
    0.87
     will
    0.87
     Likely
    0.86
     fometimes
    0.85
    Act Density 0.315%

    No Known Activations