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

    Neuronpedia

    INDEX
    Explanations

    specific sequences of letters or patterns within words

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Duch
    -0.15
    ì£
    -0.15
    unch
    -0.14
    alars
    -0.14
    елен
    -0.14
     bent
    -0.14
    _xy
    -0.14
    ÑĪки
    -0.14
    Ľå»º
    -0.13
    enheim
    -0.13
    POSITIVE LOGITS
    //:
    0.24
     dna
    0.24
    /sn
    0.20
     ret
    0.19
    gni
    0.18
     DNA
    0.18
     sno
    0.17
    olle
    0.17
     emoc
    0.17
    GN
    0.17
    Act Density 0.006%

    No Known Activations