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

    Neuronpedia

    INDEX
    Explanations

    phrases related to legal documents and procedures

    oai_token-act-pair · gpt-3.5-turbo

    punctuations and sentence delimiters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ierre
    -0.79
    ensibly
    -0.72
    apeshifter
    -0.68
     imperson
    -0.65
     marching
    -0.64
     rallying
    -0.64
    arching
    -0.63
    ogl
    -0.62
     forwarding
    -0.62
     railing
    -0.61
    POSITIVE LOGITS
     Lastly
    1.65
     Finally
    1.52
     Similarly
    1.24
     Additionally
    1.22
     Furthermore
    1.18
     Likewise
    1.18
     Alternatively
    1.17
     Nevertheless
    1.16
     Moreover
    1.16
     Conversely
    1.15
    Act Density 0.748%

    No Known Activations