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

    Neuronpedia

    INDEX
    Explanations

    names and titles of people or organizations

    oai_token-act-pair · gpt-3.5-turbo

    references to educational institutions and graduation events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     destro
    -0.74
     staggering
    -0.64
     sweeping
    -0.62
    bidden
    -0.62
     farther
    -0.61
     taboo
    -0.61
    zens
    -0.61
     downright
    -0.60
     asses
    -0.60
     nesting
    -0.60
    POSITIVE LOGITS
    <|endoftext|>
    1.16
    ↵↵
    1.13
    ↵
    1.12
     (@
    0.98
    ↵Âł
    0.96
     Correspond
    0.92
     Photographer
    0.89
     Publisher
    0.88
     Posted
    0.86
    ________________________________
    0.85
    Act Density 0.319%

    No Known Activations