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

    Neuronpedia

    INDEX
    Explanations

    occurrences of punctuation marks and their placement in surrounding text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    isches
    -0.18
    itage
    -0.17
    loff
    -0.16
    iker
    -0.16
    haus
    -0.15
    is
    -0.15
    ibe
    -0.14
    835
    -0.14
    _concat
    -0.14
     Hast
    -0.14
    POSITIVE LOGITS
    âĪ¨
    0.26
    United
    0.19
     United
    0.17
    /GPL
    0.17
    kest
    0.16
     âĪ¨
    0.16
    -Identifier
    0.16
     Names
    0.16
     âĪ§
    0.16
    Identifier
    0.15
    Act Density 0.045%

    No Known Activations