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

    Neuronpedia

    INDEX
    Explanations

    proper nouns

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Hein"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     clamp
    -0.74
    dash
    -0.71
    grade
    -0.66
    Mount
    -0.66
     monitor
    -0.66
    **
    -0.65
     hoops
    -0.65
     mud
    -0.62
     ladder
    -0.61
     monitors
    -0.61
    POSITIVE LOGITS
     Hein
    4.14
     Wilhelm
    1.40
     Ernst
    1.34
     Kraft
    1.26
     Herman
    1.22
     Von
    1.20
     Werner
    1.15
     Fra
    1.14
     Friedrich
    1.14
     Pru
    1.12
    Act Density 0.017%

    No Known Activations