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

    Neuronpedia

    INDEX
    Explanations

    various forms of punctuation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Mississippi
    -0.15
     Meh
    -0.14
    uppy
    -0.14
    ukes
    -0.14
    -aos
    -0.14
     alike
    -0.14
    Mis
    -0.13
     Hayden
    -0.13
     Abraham
    -0.13
    vr
    -0.13
    POSITIVE LOGITS
    rix
    0.15
    EncodingException
    0.15
    lod
    0.15
    esub
    0.15
    TestData
    0.15
    ovit
    0.14
    hawk
    0.14
    ernel
    0.14
    olls
    0.14
    iband
    0.14
    Act Density 0.001%

    No Known Activations