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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating the subject or topic of discussion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.08
    1:0.08
    2:0.07
    3:0.08
    4:0.07
    5:0.10
    6:0.08
    7:0.08
    8:0.08
    9:0.08
    10:0.08
    11:0.07
    Negative Logits
     Timbers
    -2.77
     Ong
    -2.76
     Yong
    -2.71
     Chong
    -2.68
     MH
    -2.64
    ocre
    -2.63
     NK
    -2.63
     Kyoto
    -2.61
     NA
    -2.57
     NR
    -2.55
    POSITIVE LOGITS
    mobile
    3.03
     mob
    2.65
     wearable
    2.58
    mob
    2.52
    fx
    2.45
     dash
    2.42
     fluid
    2.42
     eff
    2.39
    cible
    2.37
     subdivision
    2.34
    Act Density 0.000%

    No Known Activations