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

    Neuronpedia

    INDEX
    Explanations

    expressions indicating uncertainty or conditions

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

    "...or at least..."

    np_acts-logits-general · gemini-2.0-flash

    at least

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    XtraBars
    -0.47
    SequentialGroup
    -0.42
     invokingState
    -0.40
     souverain
    -0.38
    expandindo
    -0.36
     références
    -0.35
     window
    -0.35
     kaarangay
    -0.35
    WINDOW
    -0.35
     आदि
    -0.35
    POSITIVE LOGITS
     zumindest
    0.75
    indest
    0.73
     Least
    0.68
     almeno
    0.68
     least
    0.67
     atleast
    0.66
    起码
    0.66
    Least
    0.66
    least
    0.66
    jmniej
    0.65
    Act Density 0.288%

    No Known Activations