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

    Neuronpedia

    INDEX
    Explanations

    sentences that contain periods, indicating the end of statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.03
    1:0.02
    2:0.09
    3:0.11
    4:0.09
    5:0.04
    6:0.25
    7:0.09
    8:0.03
    9:0.05
    10:0.07
    11:0.06
    Negative Logits
    ��
    -2.05
    ADRA
    -1.75
    ��
    -1.59
     Debor
    -1.55
    フォ
    -1.53
    ORED
    -1.46
    ufact
    -1.44
    ��
    -1.44
     Pru
    -1.41
     submarines
    -1.41
    POSITIVE LOGITS
     google
    1.84
    graph
    1.61
    paren
    1.59
    document
    1.58
    parency
    1.58
    mite
    1.54
    talk
    1.52
    wiki
    1.49
    lab
    1.44
    research
    1.42
    Act Density 0.002%

    No Known Activations