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

    Neuronpedia

    INDEX
    Explanations

    sentences related to personal opinions or reflections

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     veil
    -0.67
    xtap
    -0.65
     WATCHED
    -0.65
     sugg
    -0.64
     plea
    -0.63
     rush
    -0.63
     drop
    -0.63
    estone
    -0.63
    tip
    -0.61
    Previously
    -0.60
    POSITIVE LOGITS
     theirs
    1.30
     hers
    1.18
     yours
    1.16
     ours
    1.12
     anybody
    0.88
     mine
    0.87
     everybody
    0.82
     others
    0.81
    everyone
    0.81
     whoever
    0.80
    Act Density 0.286%

    No Known Activations