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

    Neuronpedia

    INDEX
    Explanations

    phrases related to computer programming and technical specifications

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific "SL" or "safety law" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ria
    -0.68
    nor
    -0.68
    geons
    -0.67
    ãĥ£
    -0.65
    ãĥĦ
    -0.64
     Samar
    -0.64
    ãĥį
    -0.64
    ãĥĨãĤ£
    -0.64
    tainment
    -0.63
    tis
    -0.63
    POSITIVE LOGITS
    anguage
    1.01
    OTS
    0.97
    ength
    0.90
    OW
    0.89
    ASH
    0.88
    ACK
    0.87
    IFT
    0.87
    OCK
    0.86
    ibrary
    0.84
    UE
    0.83
    Act Density 0.017%

    No Known Activations