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

    Neuronpedia

    INDEX
    Explanations

    titles of articles or guides with instructions or tips

    oai_token-act-pair · gpt-3.5-turbo

    instructions or guides on how to perform various tasks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    court
    -0.70
    krit
    -0.68
     Wynne
    -0.68
    vic
    -0.67
    shown
    -0.66
    aris
    -0.65
    llah
    -0.65
    sold
    -0.65
    emies
    -0.65
    HI
    -0.64
    POSITIVE LOGITS
    uate
    0.84
     mult
    0.65
     efficiently
    0.65
     oneself
    0.64
     attribution
    0.62
     navigate
    0.61
    ulate
    0.61
     mentally
    0.59
     exposures
    0.58
     MG
    0.58
    Act Density 0.183%

    No Known Activations