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

    Neuronpedia

    INDEX
    Explanations

    references to reading and written communication

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.05
    1:0.04
    2:0.04
    3:0.04
    4:0.02
    5:0.03
    6:0.05
    7:0.53
    8:0.02
    9:0.03
    10:0.04
    11:0.05
    Negative Logits
    hower
    -2.13
    itionally
    -2.05
    ancial
    -2.00
    theless
    -1.92
    ADRA
    -1.84
    ikarp
    -1.79
    DragonMagazine
    -1.75
     Vik
    -1.71
    oubted
    -1.71
    levard
    -1.69
    POSITIVE LOGITS
    %:
    4.92
    .):
    4.53
    ):
    4.47
    *:
    4.45
    ]:
    4.35
    !:
    4.31
    ':
    4.06
    :
    4.06
    :[
    3.94
    ?:
    3.92
    Act Density 0.192%

    No Known Activations