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

    Neuronpedia

    INDEX
    Explanations

    strings of characters that indicate social media engagement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.06
    1:0.02
    2:0.11
    3:0.14
    4:0.03
    5:0.08
    6:0.09
    7:0.05
    8:0.10
    9:0.08
    10:0.13
    11:0.06
    Negative Logits
    CLASSIFIED
    -1.11
    illary
    -1.07
    ESCO
    -1.04
    hered
    -1.03
    ▬
    -1.01
     respectively
    -0.98
     gradient
    -0.97
     unison
    -0.97
    Saharan
    -0.94
    taboola
    -0.94
    POSITIVE LOGITS
    rez
    1.30
    dyl
    1.28
    olor
    1.24
    oston
    1.23
    ayn
    1.22
    Uk
    1.21
    _-_
    1.15
    __
    1.14
    imon
    1.13
    amas
    1.13
    Act Density 0.042%

    No Known Activations