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

    Neuronpedia

    INDEX
    Explanations

    phrases cautioning or advising carefulness

    oai_token-act-pair · gpt-3.5-turbo

    assertions or recommendations to exercise caution

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Lens
    -0.66
     Beet
    -0.64
    JECT
    -0.63
    plex
    -0.61
    volume
    -0.60
    mitt
    -0.59
     seams
    -0.57
     Feld
    -0.57
    soever
    -0.57
    minster
    -0.57
    POSITIVE LOGITS
    ary
    1.26
     caution
    0.92
    autions
    0.91
    arily
    0.91
    ously
    0.90
    aries
    0.89
    ARY
    0.83
    ificate
    0.80
    udic
    0.79
    urous
    0.79
    Act Density 0.030%

    No Known Activations