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

    Neuronpedia

    INDEX
    Explanations

    negative contractions and expressions of uncertainty or doubt

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

    until

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Personensuche
    -0.53
     cherchés
    -0.53
    WithIOException
    -0.49
    ніципалі
    -0.45
    astify
    -0.41
     <>",
    -0.41
    Edm
    -0.40
    enumi
    -0.40
     >=",
    -0.38
    enumii
    -0.38
    POSITIVE LOGITS
     until
    0.85
     untill
    0.79
    Until
    0.79
     Until
    0.78
     UNTIL
    0.76
     till
    0.72
    until
    0.66
    直到
    0.65
    直至
    0.61
     til
    0.57
    Act Density 0.057%

    No Known Activations