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

    Neuronpedia

    INDEX
    Explanations

    phrases containing descriptions or attributions

    oai_token-act-pair · gpt-3.5-turbo

    phrases that involve descriptions or characterizations of people, events, or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ettlement
    -0.61
    abiding
    -0.59
    Zone
    -0.59
    ipeg
    -0.57
    cise
    -0.56
    acion
    -0.54
     reproduce
    -0.53
    olar
    -0.53
     Lor
    -0.53
    tein
    -0.53
    POSITIVE LOGITS
     favorably
    0.90
     skept
    0.87
     unfairly
    0.86
     sarcast
    0.71
    okingly
    0.70
     by
    0.69
     errone
    0.69
     harshly
    0.68
     negatively
    0.66
    ologically
    0.66
    Act Density 0.153%

    No Known Activations