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

    Neuronpedia

    INDEX
    Explanations

    numerical and quantitative information regarding events and rankings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    715
    -0.16
    bucks
    -0.16
    casting
    -0.15
     Bundy
    -0.15
    709
    -0.15
    assing
    -0.15
    893
    -0.15
     Hills
    -0.15
    743
    -0.14
    739
    -0.14
    POSITIVE LOGITS
    32
    0.28
    16
    0.28
    64
    0.27
    128
    0.24
    8
    0.22
    256
    0.22
     sixteen
    0.22
    240
    0.20
    24
    0.20
    160
    0.19
    Act Density 0.050%

    No Known Activations