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

    Neuronpedia

    INDEX
    Explanations

    political and government-related terms or phrases

    oai_token-act-pair · gpt-3.5-turbo

    instances of commas in sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oph
    -0.70
    MpServer
    -0.66
    SON
    -0.63
    ":"/
    -0.63
    OWN
    -0.62
    irection
    -0.61
    EO
    -0.61
    ishly
    -0.60
    esta
    -0.58
     intermediary
    -0.58
    POSITIVE LOGITS
     respectively
    0.90
     namely
    0.76
     moreover
    0.74
     culminating
    0.72
     meanwhile
    0.72
     however
    0.72
     wherein
    0.70
     which
    0.68
     albeit
    0.67
    perty
    0.66
    Act Density 0.998%

    No Known Activations