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

    Neuronpedia

    INDEX
    Explanations

    technical details related to programming or software errors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.10
    1:0.07
    2:0.10
    3:0.10
    4:0.08
    5:0.09
    6:0.07
    7:0.08
    8:0.05
    9:0.05
    10:0.07
    11:0.08
    Negative Logits
    Pear
    -2.75
     Television
    -2.49
     Bowling
    -2.48
     Minority
    -2.43
     Divinity
    -2.41
     Parables
    -2.41
    endon
    -2.36
     Bombs
    -2.35
    Price
    -2.27
     Arms
    -2.25
    POSITIVE LOGITS
     rc
    3.41
     init
    3.07
     error
    2.92
     vm
    2.88
     cached
    2.81
     UTC
    2.70
     aborted
    2.63
     errors
    2.62
     daemon
    2.58
     ok
    2.58
    Act Density 0.015%

    No Known Activations