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

    Neuronpedia

    INDEX
    Explanations

    specific numerical values and references to physical documentation or evidence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.03
    1:0.03
    2:0.03
    3:0.10
    4:0.02
    5:0.04
    6:0.01
    7:0.05
    8:0.02
    9:0.01
    10:0.60
    11:0.02
    Negative Logits
     Lastly
    -2.23
    UTC
    -2.07
    ciating
    -1.87
    %.
    -1.87
    !".
    -1.87
     Quote
    -1.81
    thinkable
    -1.81
    venth
    -1.73
    ibia
    -1.70
    everything
    -1.70
    POSITIVE LOGITS
     or
    4.63
     Or
    3.81
    Or
    3.76
    Either
    3.52
     Either
    3.29
     either
    3.27
     OR
    3.13
    or
    3.05
    either
    2.62
     nor
    2.54
    Act Density 0.379%

    No Known Activations