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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate a broad scope or extensive range of options, qualities, or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     jSON
    -0.47
     napkins
    -0.46
    checkpoint
    -0.45
    logrus
    -0.44
     Kitts
    -0.42
    GORITH
    -0.42
     Cel
    -0.42
     joh
    -0.41
    computa
    -0.40
     pellic
    -0.39
    POSITIVE LOGITS
     wide
    1.46
     Wide
    1.44
    Wide
    1.40
    wide
    1.27
     WIDE
    1.20
    WIDE
    1.13
     widest
    1.13
     широкий
    1.09
     širo
    1.09
     geniş
    1.09
    Act Density 0.046%

    No Known Activations