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

    Neuronpedia

    INDEX
    Explanations

    technical terms related to modernized and automated electrical grids

    oai_token-act-pair · gpt-3.5-turbo

    instances of the letter 'T' in varying contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ment
    -0.67
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.64
    zona
    -0.61
     manif
    -0.59
     bystand
    -0.59
     Atmosp
    -0.58
     Bots
    -0.58
     destro
    -0.58
     quotes
    -0.58
     socks
    -0.58
    POSITIVE LOGITS
    ARGET
    1.42
    ractor
    1.24
    ribute
    1.22
    ruly
    1.19
    ributes
    1.18
    itles
    1.18
    OTAL
    1.18
    empt
    1.17
    olerance
    1.16
    ract
    1.15
    Act Density 0.064%

    No Known Activations