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

    Neuronpedia

    INDEX
    Explanations

    references to release dates and processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.02
    1:0.01
    2:0.21
    3:0.10
    4:0.16
    5:0.02
    6:0.05
    7:0.13
    8:0.03
    9:0.05
    10:0.11
    11:0.06
    Negative Logits
    phia
    -1.61
     advantage
    -1.42
     disadvantage
    -1.40
    advant
    -1.35
     perk
    -1.30
    SPONSORED
    -1.30
     advis
    -1.27
     advantages
    -1.24
    acebook
    -1.23
     fert
    -1.22
    POSITIVE LOGITS
    �
    1.76
    版
    1.63
    ギ
    1.60
    ��
    1.58
    �
    1.53
    interstitial
    1.39
    mouse
    1.39
    {"
    1.34
    ascus
    1.34
    anmar
    1.32
    Act Density 0.003%

    No Known Activations