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

    Neuronpedia

    INDEX
    Explanations

    expressions of numerical or statistical data

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

    numbers around 15

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    consul
    -0.59
    underwater
    -0.57
     cloche
    -0.56
    tvguidetime
    -0.56
    tunnel
    -0.55
     concierge
    -0.54
     ſind
    -0.54
     combineReducers
    -0.53
     getBy
    -0.53
     revolver
    -0.52
    POSITIVE LOGITS
     Fifteen
    0.63
    Fifteen
    0.60
     fifteen
    0.60
     quinze
    0.56
     fifteenth
    0.54
     ۱۵
    0.51
     Sixteenth
    0.48
    teen
    0.47
     Fourteen
    0.47
    ۱۵
    0.46
    Act Density 0.081%

    No Known Activations