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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate the potential for impact or influence in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    alle
    -0.20
    dden
    -0.17
    etten
    -0.17
    ngo
    -0.15
    eting
    -0.14
    Å¡ak
    -0.14
    ALLE
    -0.14
    iners
    -0.14
    utable
    -0.14
    illow
    -0.14
    POSITIVE LOGITS
    ity
    0.19
    y
    0.18
    639
    0.17
    963
    0.16
    915
    0.16
    ter
    0.16
    à¸Ļ
    0.15
    870
    0.15
    REFERRED
    0.15
    Coder
    0.14
    Act Density 0.025%

    No Known Activations