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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "go."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.07
    1:0.08
    2:0.09
    3:0.08
    4:0.07
    5:0.08
    6:0.08
    7:0.08
    8:0.06
    9:0.08
    10:0.09
    11:0.08
    Negative Logits
    que
    -2.38
     rall
    -2.37
     humanitarian
    -2.26
    iop
    -2.15
     advoc
    -2.13
     Palestin
    -2.11
    aho
    -2.11
     裏�
    -2.10
    NK
    -2.10
     rg
    -2.10
    POSITIVE LOGITS
     bruises
    2.12
     bruising
    2.10
    hair
    2.06
    axy
    2.00
    idia
    1.99
    wives
    1.99
    levision
    1.93
    aura
    1.87
     Appearance
    1.85
    iring
    1.84
    Act Density 0.000%

    No Known Activations