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

    Neuronpedia

    INDEX
    Explanations

    technical instructions or steps

    oai_token-act-pair · gpt-3.5-turbo

    parentheses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     impeachment
    -0.72
     pale
    -0.72
     spir
    -0.71
     lull
    -0.71
     wre
    -0.71
     inund
    -0.70
     retard
    -0.70
     confront
    -0.69
     prey
    -0.68
     sharply
    -0.67
    POSITIVE LOGITS
    including
    1.36
    possibly
    1.36
    sic
    1.31
    excluding
    1.31
    which
    1.29
    via
    1.28
    usually
    1.26
    ?)
    1.26
    optional
    1.26
    depending
    1.25
    Act Density 0.187%

    No Known Activations