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

    Neuronpedia

    INDEX
    Explanations

    numeric values and formatting elements in a data-driven context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    348
    -0.16
    2
    -0.14
    3
    -0.14
    23
    -0.14
    áo
    -0.14
    beh
    -0.13
    472
    -0.13
    237
    -0.13
    åde
    -0.13
    28
    -0.13
    POSITIVE LOGITS
    100
    0.79
     hundred
    0.59
     Hundred
    0.56
    101
    0.46
    çĻ¾
    0.46
     çĻ¾
    0.43
    undred
    0.38
    102
    0.36
    ¡
    0.32
    103
    0.31
    Act Density 0.028%

    No Known Activations