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

    Neuronpedia

    INDEX
    Explanations

    references to specific entities or groups of things

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.08
    1:0.03
    2:0.09
    3:0.07
    4:0.07
    5:0.05
    6:0.17
    7:0.05
    8:0.07
    9:0.17
    10:0.04
    11:0.07
    Negative Logits
     Cleveland
    -3.87
    Gil
    -3.65
     Browns
    -3.64
     Irving
    -3.62
     Gilbert
    -3.52
    orsche
    -3.37
    oug
    -3.36
    Ford
    -3.34
     Ohio
    -3.33
     mart
    -3.30
    POSITIVE LOGITS
     parasites
    8.05
     parasite
    7.54
     Paras
    7.26
     paras
    6.73
     parasitic
    6.36
     larvae
    5.79
     lar
    5.32
     malaria
    4.82
    iasis
    4.48
     cater
    4.28
    Act Density 0.001%

    No Known Activations