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

    Neuronpedia

    INDEX
    Explanations

    instances of personal engagement and emotional responses to media or entertainment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.02
    1:0.01
    2:0.06
    3:0.06
    4:0.07
    5:0.05
    6:0.03
    7:0.05
    8:0.06
    9:0.06
    10:0.39
    11:0.07
    Negative Logits
     subordinate
    -1.84
    leaders
    -1.84
    vati
    -1.81
     subcontract
    -1.79
     sche
    -1.70
     commanding
    -1.68
     Miko
    -1.67
     Immunity
    -1.65
     recruitment
    -1.64
     Vander
    -1.63
    POSITIVE LOGITS
     binge
    2.20
    Reader
    2.19
    aptop
    2.11
    taboola
    2.04
    scan
    2.01
    iences
    1.95
    Reviewed
    1.91
    Scan
    1.90
     consume
    1.86
    glomer
    1.85
    Act Density 0.098%

    No Known Activations