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

    Neuronpedia

    INDEX
    Explanations

    sequences of numbers or identifiers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     e
    -0.47
    2
    -0.45
     Mar
    -0.42
     
    -0.42
     of
    -0.41
    <eos>
    -0.41
    les
    -0.41
     ag
    -0.39
     mai
    -0.39
    <h1>
    -0.39
    POSITIVE LOGITS
    AndEndTag
    1.32
    Datuak
    1.19
    SourceChecksum
    1.16
    StoryboardSegue
    1.14
    دانشنامهٔ
    1.11
     للاسماء
    1.10
    ValueStyle
    1.08
    Personensuche
    1.07
    fjspx
    1.05
    KURZBESCHREIBUNG
    1.04
    Act Density 0.383%

    No Known Activations