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

    Neuronpedia

    INDEX
    Explanations

    legal terminology and references to court cases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Mike
    -0.18
     Doc
    -0.17
    Mike
    -0.17
    Matt
    -0.16
     Dave
    -0.16
    uzzi
    -0.16
     Matt
    -0.15
    Jim
    -0.15
     Jim
    -0.15
    ffi
    -0.15
    POSITIVE LOGITS
     William
    0.27
    William
    0.25
     Ronald
    0.25
     Kenneth
    0.24
     Timothy
    0.23
     Douglas
    0.22
     Edward
    0.22
     Donald
    0.21
    Donald
    0.21
     Frederick
    0.20
    Act Density 0.169%

    No Known Activations