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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating comparisons or measurements related to performance or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ---</
    -0.16
     ÙħاÙĬ
    -0.16
    .checkNotNull
    -0.15
     —↵↵
    -0.15
    ênh
    -0.15
    INFRINGEMENT
    -0.14
    ighet
    -0.14
    .PerformLayout
    -0.14
    qus
    -0.14
    HeaderCode
    -0.14
    POSITIVE LOGITS
     only
    0.25
     its
    0.21
     ONLY
    0.21
     which
    0.19
    only
    0.19
     Only
    0.19
     would
    0.18
    Only
    0.18
     Its
    0.16
     wouldn
    0.16
    Act Density 0.007%

    No Known Activations