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

    Neuronpedia

    INDEX
    Explanations

    terms related to community and connections among people

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.06
    1:0.14
    2:0.07
    3:0.09
    4:0.02
    5:0.14
    6:0.04
    7:0.02
    8:0.09
    9:0.10
    10:0.08
    11:0.10
    Negative Logits
    �醒
    -1.81
    ynthesis
    -1.67
    nown
    -1.60
    ワン
    -1.57
    pection
    -1.55
     Helic
    -1.50
     hindsight
    -1.47
     Tes
    -1.39
    sych
    -1.38
    unn
    -1.38
    POSITIVE LOGITS
     enthusi
    1.69
     charism
    1.51
    SPONSORED
    1.45
    ient
    1.38
    Feel
    1.37
     selves
    1.37
     flair
    1.36
     thinkers
    1.36
     Rodham
    1.33
     obliged
    1.32
    Act Density 0.000%

    No Known Activations