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

    Neuronpedia

    INDEX
    Explanations

    the word "or."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.09
    1:0.07
    2:0.08
    3:0.08
    4:0.08
    5:0.09
    6:0.07
    7:0.07
    8:0.07
    9:0.08
    10:0.09
    11:0.08
    Negative Logits
    HUD
    -2.99
    compliance
    -2.88
    nergy
    -2.78
    ceptor
    -2.74
    rio
    -2.63
    OSH
    -2.63
    opoly
    -2.62
    Mods
    -2.58
    Customer
    -2.58
    engine
    -2.57
    POSITIVE LOGITS
     Cay
    2.61
     airst
    2.60
     autobiography
    2.53
     Alicia
    2.52
     Alaska
    2.43
     Misty
    2.43
    ansk
    2.42
     adventurer
    2.40
     lapt
    2.40
     Alz
    2.38
    Act Density 0.000%

    No Known Activations