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

    Neuronpedia

    INDEX
    Explanations

    the name "Kat" with different endings and variations

    oai_token-act-pair · gpt-3.5-turbo

    the name "Kat" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Urug
    -0.75
    \\\\
    -0.74
     freeway
    -0.73
    NFL
    -0.72
    overe
    -0.71
    ±
    -0.70
    ential
    -0.70
     Uruguay
    -0.69
     automate
    -0.67
    usted
    -0.65
    POSITIVE LOGITS
     Kat
    3.82
    Kat
    2.91
    kat
    2.27
     Kath
    1.83
     Kats
    1.68
     Katz
    1.55
     Sok
    1.48
     Kar
    1.28
     Hatt
    1.25
     Krist
    1.20
    Act Density 0.026%

    No Known Activations