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

    Neuronpedia

    INDEX
    Explanations

    sequences that resemble identifiers or codes, likely for tracking or data purposes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    strup
    -0.16
     bl
    -0.15
    upo
    -0.15
    nger
    -0.15
    ãĥ³ãĥij
    -0.14
    ;amp
    -0.14
     undef
    -0.14
    ularity
    -0.14
    ople
    -0.14
    hir
    -0.14
    POSITIVE LOGITS
    Structured
    0.15
    otta
    0.15
    åį·
    0.15
    cak
    0.14
    ë§ī
    0.14
    ä¼ı
    0.14
    ="../../../
    0.14
    rior
    0.14
    ÏĦή
    0.14
    WM
    0.13
    Act Density 0.007%

    No Known Activations