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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and their frequencies within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    acher
    -0.16
    aria
    -0.14
    üm
    -0.14
    /Foundation
    -0.14
    ostel
    -0.14
    aiser
    -0.14
    ADIO
    -0.13
    /portfolio
    -0.13
     Grip
    -0.13
     zwar
    -0.13
    POSITIVE LOGITS
     according
    0.18
     said
    0.15
    quam
    0.15
    -hook
    0.15
    olin
    0.15
    idon
    0.15
     kla
    0.14
    logan
    0.14
    ear
    0.14
    empt
    0.14
    Act Density 0.157%

    No Known Activations