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

    Neuronpedia

    INDEX
    Explanations

    numerical values and references related to classifications or identifiers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    REDIT
    -0.14
     Bowling
    -0.14
    ãĤ·ãĥ§ãĥ³
    -0.14
     ilma
    -0.14
    asure
    -0.13
    reamble
    -0.13
     respectively
    -0.13
    versions
    -0.13
     Guarantee
    -0.13
    opher
    -0.13
    POSITIVE LOGITS
    erman
    0.14
    jah
    0.14
    oui
    0.14
    oyal
    0.13
    øj
    0.13
    æŀļ
    0.13
    iga
    0.13
    ocy
    0.13
     Fem
    0.13
    inge
    0.13
    Act Density 0.001%

    No Known Activations