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

    Neuronpedia

    INDEX
    Explanations

    words related to referrals or recommendations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.08
    1:0.09
    2:0.08
    3:0.09
    4:0.06
    5:0.07
    6:0.08
    7:0.08
    8:0.08
    9:0.08
    10:0.08
    11:0.08
    Negative Logits
     Activity
    -3.10
     Offline
    -3.02
     Chapters
    -3.01
     Rune
    -2.90
     Application
    -2.78
     eBook
    -2.74
     Melee
    -2.69
     Learns
    -2.66
     Berry
    -2.64
     Sessions
    -2.63
    POSITIVE LOGITS
    flo
    3.10
    LOS
    2.93
     ducks
    2.92
    ilater
    2.71
     ignor
    2.67
    prep
    2.60
    clock
    2.57
     steer
    2.53
    LR
    2.53
    pher
    2.52
    Act Density 0.000%

    No Known Activations