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

    Neuronpedia

    INDEX
    Explanations

    phrases related to official statements and press releases

    oai_token-act-pair · gpt-3.5-turbo

    statements or announcements from organizations or individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Penet
    -0.68
    pei
    -0.63
     grind
    -0.62
    grade
    -0.61
    sten
    -0.61
     jugg
    -0.60
     calculus
    -0.60
     eyed
    -0.60
    plot
    -0.60
     Bunker
    -0.60
    POSITIVE LOGITS
    Statement
    0.91
     requesting
    0.78
     behalf
    0.77
     announcing
    0.75
     thanking
    0.70
     Regarding
    0.70
     responding
    0.70
     stating
    0.69
     spokesperson
    0.68
    statement
    0.67
    Act Density 0.312%

    No Known Activations