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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a relationship or connection between entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.03
    1:0.02
    2:0.07
    3:0.07
    4:0.11
    5:0.02
    6:0.04
    7:0.39
    8:0.03
    9:0.03
    10:0.07
    11:0.07
    Negative Logits
    ceivable
    -1.67
    cand
    -1.56
     noises
    -1.55
     dra
    -1.50
    spir
    -1.50
    ient
    -1.50
    elf
    -1.49
     temp
    -1.39
     balloons
    -1.38
     mixture
    -1.37
    POSITIVE LOGITS
    hler
    1.79
     Wikimedia
    1.68
    endez
    1.66
    ureau
    1.57
    ilan
    1.56
     Inher
    1.53
    ESA
    1.51
    saf
    1.51
    iatus
    1.51
    negie
    1.50
    Act Density 0.000%

    No Known Activations