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

    Neuronpedia

    INDEX
    Explanations

    phrases related to deriving lessons or insights from experiences

    oai_token-act-pair · gpt-3.5-turbo

    phrases that involve learning or gaining knowledge from experiences or individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hai
    -0.80
    stem
    -0.80
    aque
    -0.70
     stoked
    -0.70
    isode
    -0.69
    mask
    -0.67
    priority
    -0.67
    perture
    -0.66
    ifling
    -0.66
    quote
    -0.66
    POSITIVE LOGITS
     afar
    1.34
     whence
    1.12
     scratch
    1.03
     thence
    0.86
     inside
    0.72
     elsewhere
    0.71
     anywhere
    0.70
     within
    0.68
     wherever
    0.68
     across
    0.68
    Act Density 0.096%

    No Known Activations