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

    Neuronpedia

    INDEX
    Explanations

    uppercase words, possibly acronyms or titles

    oai_token-act-pair · gpt-3.5-turbo

    capital letters and acronyms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    clinton
    -0.78
    Magikarp
    -0.73
    yip
    -0.72
    Ô
    -0.69
    culosis
    -0.67
    DragonMagazine
    -0.67
    hyde
    -0.66
    wolves
    -0.65
    artifacts
    -0.65
    cair
    -0.64
    POSITIVE LOGITS
    inct
    0.87
    achment
    0.84
    amped
    0.83
    ached
    0.79
    erving
    0.79
    ubs
    0.77
    akable
    0.75
    amps
    0.74
    itt
    0.74
    erves
    0.73
    Act Density 0.068%

    No Known Activations