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

    Neuronpedia

    INDEX
    Explanations

    references to programming functions and structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     twenty
    -0.25
    22
    -0.24
    21
    -0.23
    23
    -0.23
    24
    -0.23
     Twenty
    -0.23
    twenty
    -0.21
    äºĮåįģ
    -0.20
    Twenty
    -0.20
    25
    -0.18
    POSITIVE LOGITS
    0.36
    0.36
    0.32
    0.28
    0.27
    0.24
    0.24
    0.23
    itten
    0.22
    ----------------------------
    0.22
    Act Density 0.010%

    No Known Activations