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

    Neuronpedia

    INDEX
    Explanations

    hexadecimal characters and sequences, particularly in the context of encoding or signatures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ð
    -0.16
    ī
    -0.15
    585
    -0.14
     Stud
    -0.14
    esian
    -0.14
    zee
    -0.14
    ames
    -0.13
     ð
    -0.13
    572
    -0.13
    416
    -0.13
    POSITIVE LOGITS
    ouver
    0.15
    bern
    0.15
     uns
    0.15
     Geile
    0.15
    ULD
    0.14
    ıa
    0.14
    CKER
    0.13
    conde
    0.13
    æľĭ
    0.13
    umbo
    0.13
    Act Density 0.002%

    No Known Activations