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

    Neuronpedia

    INDEX
    Explanations

    words related to names or identifiers associated with places or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.01
    1:0.02
    2:0.03
    3:0.04
    4:0.03
    5:0.02
    6:0.41
    7:0.21
    8:0.02
    9:0.03
    10:0.08
    11:0.03
    Negative Logits
    ufact
    -2.00
    AUD
    -1.55
    icrobial
    -1.53
    ICAN
    -1.37
    redients
    -1.35
    arians
    -1.34
    ベ
    -1.31
    aple
    -1.29
    ////////////////////////////////
    -1.28
    acebook
    -1.26
    POSITIVE LOGITS
    larg
    1.40
    river
    1.39
    united
    1.36
     levers
    1.35
    EStream
    1.28
     fortunes
    1.23
     limb
    1.23
    wagen
    1.21
    xon
    1.19
    sighted
    1.19
    Act Density 0.000%

    No Known Activations