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

    Neuronpedia

    INDEX
    Explanations

    instances where the word "say" is used in a sentence

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    obal
    -0.80
    aughs
    -0.76
    leeve
    -0.74
    Justice
    -0.70
    ctic
    -0.68
    andem
    -0.68
    ament
    -0.65
    kefeller
    -0.65
     destro
    -0.65
    ressive
    -0.64
    POSITIVE LOGITS
     goodbye
    0.81
    lihood
    0.80
    parts
    0.76
     hello
    0.72
     Pearce
    0.65
     Schr
    0.63
     Nab
    0.60
     Angela
    0.60
     Bacon
    0.60
     Dunk
    0.60
    Act Density 0.020%

    No Known Activations