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

    Neuronpedia

    INDEX
    Explanations

    occurrences of personal pronouns and phrases indicative of human interaction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     nepÅĻÃŃ
    -0.16
     máºŃt
    -0.15
    essel
    -0.14
     deprivation
    -0.14
     depr
    -0.14
     derec
    -0.14
     heed
    -0.14
     Forgot
    -0.13
     ignorance
    -0.13
     shorten
    -0.13
    POSITIVE LOGITS
     slow
    0.54
     slower
    0.50
     slowed
    0.49
     Slow
    0.49
    Slow
    0.47
    slow
    0.46
     delay
    0.44
     Delay
    0.44
    delay
    0.44
    Delay
    0.44
    Act Density 0.017%

    No Known Activations