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

    Neuronpedia

    INDEX
    Explanations

    phrases with the word "figured" followed by a number

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "I figured" indicating personal realizations or thoughts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    idium
    -0.72
    pes
    -0.72
    Real
    -0.69
    vette
    -0.67
    ewitness
    -0.65
    apes
    -0.65
    reports
    -0.65
    kw
    -0.65
     Machina
    -0.63
    perty
    -0.63
    POSITIVE LOGITS
    sonian
    0.92
     prominently
    0.83
    istically
    0.80
     Rasmussen
    0.67
     Ducks
    0.65
     underdog
    0.63
     strategically
    0.63
    utory
    0.62
    inery
    0.62
     Haram
    0.61
    Act Density 0.026%

    No Known Activations