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

    Neuronpedia

    INDEX
    Explanations

    references to media influence, results, and underlying systems in society

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.02
    1:0.02
    2:0.08
    3:0.08
    4:0.36
    5:0.04
    6:0.04
    7:0.13
    8:0.04
    9:0.03
    10:0.05
    11:0.06
    Negative Logits
    onge
    -1.67
    yip
    -1.65
    outheast
    -1.57
    URI
    -1.53
    uu
    -1.51
    ustomed
    -1.50
    elope
    -1.48
    scrib
    -1.48
    osponsors
    -1.45
    swer
    -1.41
    POSITIVE LOGITS
    thood
    1.59
    Bridge
    1.54
     MSG
    1.45
     dash
    1.44
     Caption
    1.44
     Trilogy
    1.41
     Velvet
    1.38
     deliberations
    1.38
    ogenesis
    1.37
     experiments
    1.37
    Act Density 0.018%

    No Known Activations