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

    Neuronpedia

    INDEX
    Explanations

    cases and scenarios that prompt questions or speculation

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "what the" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    APTER
    -0.73
    NetMessage
    -0.68
    pox
    -0.67
    mur
    -0.67
    mma
    -0.65
    Lago
    -0.63
    DragonMagazine
    -0.63
    mop
    -0.63
    gra
    -0.63
    quire
    -0.62
    POSITIVE LOGITS
     heck
    0.92
    Ĥª
    0.92
    ologically
    0.77
     fuss
    0.76
     difference
    0.75
     likes
    0.72
     labels
    0.70
     ple
    0.69
     happened
    0.66
     happens
    0.66
    Act Density 0.130%

    No Known Activations