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

    Neuronpedia

    INDEX
    Explanations

    numerical values and their relationships within a context of transactions or scoring

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bucks
    -0.18
    OPY
    -0.16
     Hills
    -0.16
     Bundy
    -0.15
    casting
    -0.15
    -Smith
    -0.15
     Bucks
    -0.15
    affer
    -0.15
    ords
    -0.15
    .Offset
    -0.15
    POSITIVE LOGITS
    128
    0.26
    64
    0.24
    32
    0.24
    16
    0.24
    256
    0.22
    512
    0.21
    640
    0.20
    240
    0.20
     sixteen
    0.20
    160
    0.19
    Act Density 0.033%

    No Known Activations