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

    Neuronpedia

    INDEX
    Explanations

    occurrences of periods in text, indicating punctuation or sentence endings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.03
    1:0.01
    2:0.30
    3:0.04
    4:0.04
    5:0.02
    6:0.12
    7:0.22
    8:0.03
    9:0.04
    10:0.04
    11:0.06
    Negative Logits
    paces
    -1.60
    translation
    -1.59
    hops
    -1.53
    taboola
    -1.52
    ometers
    -1.47
    vous
    -1.46
    wcs
    -1.43
    idays
    -1.43
    iries
    -1.42
    issions
    -1.41
    POSITIVE LOGITS
     Jr
    1.79
    Jr
    1.77
    �士
    1.59
     Sr
    1.49
    axe
    1.49
     Surviv
    1.40
     whistlebl
    1.37
    Unt
    1.36
     Forth
    1.33
    TI
    1.32
    Act Density 0.015%

    No Known Activations