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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "kind" followed by a number or phrase

    oai_token-act-pair · gpt-3.5-turbo

    phrases referring to types or categories of things

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Doors
    -0.65
     Kod
    -0.64
     Bars
    -0.60
    WOR
    -0.57
    ulia
    -0.56
     Balls
    -0.56
    ropolitan
    -0.55
    ModLoader
    -0.52
     Rio
    -0.52
     Scrib
    -0.52
    POSITIVE LOGITS
     of
    1.04
    of
    0.93
    Of
    0.90
    lihood
    0.83
     OF
    0.81
     thereof
    0.80
     Of
    0.78
    liest
    0.76
    face
    0.75
    hearted
    0.75
    Act Density 0.041%

    No Known Activations