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

    Neuronpedia

    INDEX
    Explanations

    phrases related to reflecting or representing a wide variety of concepts or characteristics

    oai_token-act-pair · gpt-3.5-turbo

    phrases discussing reflections or representations of various subjects or themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Nadu
    -0.63
    BSD
    -0.63
    acea
    -0.62
    asus
    -0.60
    wings
    -0.60
    zilla
    -0.59
    INGTON
    -0.59
    grounds
    -0.59
     Tickets
    -0.59
     Explosion
    -0.59
    POSITIVE LOGITS
    raph
    0.83
     realities
    0.81
     wishes
    0.78
     sentiments
    0.78
     sentiment
    0.76
    pter
    0.74
    abal
    0.72
    xual
    0.72
     seriousness
    0.69
    raught
    0.67
    Act Density 0.152%

    No Known Activations