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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating moments in time or pauses in action

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

    Time-related words ("moment," "minute," "second")

    np_acts-logits-general · gemini-2.0-flash

    short time units

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     linkovi
    -0.69
    webElementXpaths
    -0.66
    AndEndTag
    -0.65
    IndentedString
    -0.64
    $_['
    -0.64
    aarrggbb
    -0.62
    addCriterion
    -0.61
     noDo
    -0.60
     newOwner
    -0.59
    DateField
    -0.59
    POSITIVE LOGITS
     moment
    2.15
     moments
    1.92
    moment
    1.84
     Moment
    1.68
     minute
    1.64
    Moment
    1.63
     Moments
    1.59
    moments
    1.58
     seconds
    1.51
     MOMENT
    1.50
    Act Density 0.173%

    No Known Activations