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

    Neuronpedia

    INDEX
    Explanations

    phrases prompting the reader to take action or pay attention to specific information

    oai_token-act-pair · gpt-3.5-turbo

    phrases that emphasize certainty and encourage action

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    MpServer
    -0.85
    TPPStreamerBot
    -0.82
    impl
    -0.74
    oub
    -0.68
    bled
    -0.68
    omal
    -0.67
    Imagine
    -0.66
    gery
    -0.65
    folk
    -0.64
    Closure
    -0.63
    POSITIVE LOGITS
     checking
    0.76
     beforehand
    0.70
     Shogun
    0.70
    !:
    0.69
    icio
    0.64
     beware
    0.63
     clicking
    0.63
    appropriate
    0.63
     patience
    0.62
     Merrill
    0.62
    Act Density 0.046%

    No Known Activations