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

    Neuronpedia

    INDEX
    Explanations

    references to literature reviews and synthesis of prior research

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    449
    -0.17
    apor
    -0.16
    олом
    -0.15
     pad
    -0.14
    occo
    -0.14
    .rdf
    -0.14
    -pad
    -0.14
    ABEL
    -0.14
    awah
    -0.14
    orough
    -0.13
    POSITIVE LOGITS
     literature
    0.31
     Literature
    0.24
     published
    0.22
     recent
    0.21
     existing
    0.19
    liter
    0.19
    æĸĩçĮ®
    0.19
    published
    0.17
    references
    0.17
     liter
    0.17
    Act Density 0.120%

    No Known Activations