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

    Neuronpedia

    INDEX
    Explanations

    references to various forms of assessment and comparison

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ñĩини
    -0.14
    warts
    -0.14
    anga
    -0.14
    ÙħÙĨÛĮ
    -0.14
    _perms
    -0.14
    õi
    -0.13
    ÑıÑĩ
    -0.13
    abeth
    -0.13
    essen
    -0.13
    ãĥ¬ãĥĵ
    -0.13
    POSITIVE LOGITS
     shall
    0.24
     witnesses
    0.24
     too
    0.22
     Witnesses
    0.21
     witness
    0.21
     cat
    0.20
     Witness
    0.20
     major
    0.20
     fetch
    0.19
    Fetch
    0.19
    Act Density 0.316%

    No Known Activations