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

    Neuronpedia

    INDEX
    Explanations

    numerical patterns and values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bol
    -0.16
     ExecutionContext
    -0.15
    ear
    -0.14
    ettle
    -0.14
    orth
    -0.14
    år
    -0.13
     Hort
    -0.13
    iliary
    -0.13
     Hil
    -0.13
     fug
    -0.13
    POSITIVE LOGITS
    ynamo
    0.15
    anian
    0.14
    ród
    0.13
    ché
    0.13
    æ´
    0.13
    ãĥķãĥ¬
    0.13
    ñana
    0.13
    ãĤ¯ãĤ·ãĥ§ãĥ³
    0.13
    _MEMBERS
    0.13
    lsen
    0.13
    Act Density 0.027%

    No Known Activations