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

    Neuronpedia

    INDEX
    Explanations

    terms related to laws, regulations, and conditions of specific scenarios

    oai_token-act-pair · gpt-3.5-turbo

    instances of slashes used in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Scrib
    -0.86
     Shooter
    -0.66
     Hip
    -0.66
     guid
    -0.62
     tabl
    -0.61
     millionaires
    -0.61
     achie
    -0.61
     Progress
    -0.60
     aspir
    -0.59
     chatter
    -0.59
    POSITIVE LOGITS
    or
    1.01
    possibly
    1.00
    probably
    0.99
    maybe
    0.94
    say
    0.93
    especially
    0.93
    usually
    0.93
    \/\/
    0.93
    sometimes
    0.92
    mostly
    0.91
    Act Density 0.022%

    No Known Activations