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

    Neuronpedia

    INDEX
    Explanations

    terms signaling the need for explanation or justification

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to explaining concepts or phenomena

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sembly
    -0.79
    ngth
    -0.72
    Ranked
    -0.70
    opers
    -0.68
    ches
    -0.66
    ille
    -0.65
    net
    -0.63
    inion
    -0.63
    illet
    -0.62
    estial
    -0.61
    POSITIVE LOGITS
     why
    1.35
     WHY
    1.20
    why
    1.12
     explanations
    0.87
    ĸļ
    0.81
    Origin
    0.79
     how
    0.78
     disapp
    0.78
    abl
    0.73
     away
    0.72
    Act Density 0.058%

    No Known Activations