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

    Neuronpedia

    INDEX
    Explanations

    numerical references and age-related information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Fifty
    -0.28
     fifty
    -0.25
     forty
    -0.25
     Forty
    -0.25
     sixty
    -0.24
     seventy
    -0.21
     äºĶ
    -0.21
    Û´
    -0.20
    58
    -0.20
    53
    -0.20
    POSITIVE LOGITS
    18
    0.62
    17
    0.59
    19
    0.58
    16
    0.56
    20
    0.50
    15
    0.50
    21
    0.46
    14
    0.42
    22
    0.42
     eighteen
    0.38
    Act Density 0.243%

    No Known Activations