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

    Neuronpedia

    INDEX
    Explanations

    phrases related to comparisons and distinctions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     contradictory
    -0.15
    ÅĻi
    -0.15
    ÑĢÑĥб
    -0.14
    bulan
    -0.14
    decltype
    -0.14
    ÐĶÐļ
    -0.14
    alink
    -0.14
    ứng
    -0.14
    adera
    -0.13
     inconsistent
    -0.13
    POSITIVE LOGITS
     difference
    0.84
     differences
    0.80
     Difference
    0.74
    difference
    0.73
     Differences
    0.70
    Difference
    0.69
    å·®
    0.61
    _difference
    0.55
     diffé
    0.53
    ifference
    0.52
    Act Density 0.421%

    No Known Activations