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

    Neuronpedia

    INDEX
    Explanations

    characters or elements typically found in programming or code syntax

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    <eos>
    -0.56
      
    -0.51
     …
    -0.45
    …
    -0.45
     ang
    -0.45
     la
    -0.44
    avyzd
    -0.43
    ParallelGroup
    -0.43
     his
    -0.43
     also
    -0.42
    POSITIVE LOGITS
     متعلقه
    0.89
     avoient
    0.82
     Efq
    0.78
     purpoſe
    0.77
     &___
    0.76
     Theſe
    0.76
    ➟
    0.75
     étoient
    0.74
    Spoljašnje
    0.72
     Jefus
    0.71
    Act Density 0.871%

    No Known Activations