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

    Neuronpedia

    INDEX
    Explanations

    acronyms related to various fields

    oai_token-act-pair · gpt-3.5-turbo

    references to social media and networking platforms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tons
    -0.86
    wings
    -0.74
    gie
    -0.68
     Kali
    -0.67
    nuts
    -0.65
     mund
    -0.65
     Emirates
    -0.65
     Emir
    -0.63
    flies
    -0.63
     Hindu
    -0.59
    POSITIVE LOGITS
    OW
    1.17
    ASH
    0.93
    MP
    0.92
    APP
    0.91
    SN
    0.90
    ACK
    0.88
    ATCH
    0.88
    ³
    0.87
    OOK
    0.87
    OV
    0.87
    Act Density 0.022%

    No Known Activations