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

    Neuronpedia

    INDEX
    Explanations

    punctuations and formatting symbols in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aph
    -0.16
    hn
    -0.15
    chant
    -0.14
    ienes
    -0.14
    ило
    -0.14
    APH
    -0.14
    .bind
    -0.14
    akat
    -0.14
    ÑĥÑĢÑģ
    -0.14
     PRI
    -0.14
    POSITIVE LOGITS
     Nile
    0.16
    ाà¤ĩम
    0.15
    IMUM
    0.14
    asan
    0.13
     Kendall
    0.13
    inge
    0.13
     FITNESS
    0.13
     fis
    0.13
    .getWindow
    0.13
    iez
    0.13
    Act Density 0.004%

    No Known Activations