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

    Neuronpedia

    INDEX
    Explanations

    punctuation and class declarations within code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eman
    -0.17
    qa
    -0.15
    cycl
    -0.14
    gere
    -0.14
    marsh
    -0.14
    ety
    -0.14
     Tmax
    -0.14
    ultiply
    -0.13
    ØŃ
    -0.13
    Attrs
    -0.13
    POSITIVE LOGITS
     priv
    0.15
    RIA
    0.15
    .Companion
    0.14
    adil
    0.14
    unei
    0.14
    ITIONS
    0.14
    037
    0.14
    907
    0.14
    propri
    0.14
    èĭĹ
    0.14
    Act Density 0.002%

    No Known Activations