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

    Neuronpedia

    INDEX
    Explanations

    various instances of the word "fools" within the text

    oai_token-act-pair · gpt-3.5-turbo

    references to tools and resources, particularly in the context of gaming or software

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     fore
    -0.65
     bore
    -0.64
     pursued
    -0.63
     wartime
    -0.61
     character
    -0.60
    HC
    -0.59
     Phantom
    -0.59
     Canadian
    -0.59
     HC
    -0.58
     IM
    -0.58
    POSITIVE LOGITS
    ools
    4.87
    ool
    1.43
    OOL
    1.04
    ews
    1.02
    ypes
    1.01
    urses
    0.99
    orks
    0.98
    ilib
    0.97
    ilts
    0.96
     fools
    0.93
    Act Density 0.008%

    No Known Activations