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

    Neuronpedia

    INDEX
    Explanations

    patterns related to specific characters or strings in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Mailer
    -0.16
    ertia
    -0.15
    .fm
    -0.14
    170
    -0.14
     ì¶ľ
    -0.14
    anford
    -0.14
    zzle
    -0.14
    åĪº
    -0.14
    497
    -0.14
    urma
    -0.14
    POSITIVE LOGITS
     capital
    0.22
     lowercase
    0.20
    capital
    0.20
    asco
    0.20
     Capital
    0.19
     uppercase
    0.18
    -capital
    0.17
     capitalized
    0.17
     writ
    0.15
    شت
    0.15
    Act Density 0.082%

    No Known Activations