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

    Neuronpedia

    INDEX
    Explanations

    occurrences of personal pronouns and subjective expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     realise
    -0.18
    adic
    -0.15
     realize
    -0.15
    #__
    -0.14
     realizes
    -0.14
     desired
    -0.14
     wished
    -0.14
    ķĮ
    -0.14
     wanted
    -0.14
     realization
    -0.14
    POSITIVE LOGITS
     heard
    0.44
     saw
    0.42
     Saw
    0.40
    heard
    0.39
     Heard
    0.35
    seen
    0.33
     seen
    0.30
    Seen
    0.29
     observed
    0.27
     Seen
    0.27
    Act Density 0.213%

    No Known Activations