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

    Neuronpedia

    INDEX
    Explanations

    phrases and actions related to subscription and support for journalism

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.02
    1:0.02
    2:0.13
    3:0.17
    4:0.05
    5:0.03
    6:0.09
    7:0.05
    8:0.06
    9:0.07
    10:0.15
    11:0.11
    Negative Logits
    uthor
    -1.50
    trace
    -1.34
    hift
    -1.32
    alog
    -1.31
    axter
    -1.31
    eway
    -1.30
    tesy
    -1.28
    alogy
    -1.27
    ajor
    -1.27
    ilts
    -1.25
    POSITIVE LOGITS
    interstitial
    1.48
    �
    1.36
     Celeb
    1.33
    ��士
    1.32
     Celebr
    1.31
    Social
    1.31
     Meditation
    1.30
    Heart
    1.29
     Grammy
    1.25
    ゼ
    1.25
    Act Density 0.008%

    No Known Activations