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

    Neuronpedia

    INDEX
    Explanations

    phrases prefixed with "i.e." indicating an explanation or clarification

    oai_token-act-pair · gpt-3.5-turbo

    the letter 'e' in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    avorite
    -0.67
     mids
    -0.66
    rament
    -0.66
     encount
    -0.63
     centre
    -0.59
    last
    -0.59
     crunch
    -0.58
     cause
    -0.55
     sights
    -0.54
    ÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤ
    -0.53
    POSITIVE LOGITS
    clair
    1.03
    .,
    0.92
    clusive
    0.80
    tainment
    0.76
    ardless
    0.75
    ichen
    0.73
    gypt
    0.73
    viously
    0.73
    raq
    0.72
    hey
    0.72
    Act Density 0.017%

    No Known Activations