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

    Neuronpedia

    INDEX
    Explanations

    personal statements or actions

    oai_token-act-pair · gpt-3.5-turbo

    phrases containing the pronoun "I" and variations of it, indicating personal experiences or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    GoldMagikarp
    -0.71
    rising
    -0.68
    URI
    -0.68
     citiz
    -0.63
    ceived
    -0.63
     Leban
    -0.62
    IFIED
    -0.62
     Rising
    -0.61
     concluding
    -0.61
    ß
    -0.60
    POSITIVE LOGITS
     specialize
    1.13
     tend
    1.04
     try
    1.03
     usually
    1.02
     practise
    1.01
     strive
    1.00
     rotate
    1.00
     spend
    1.00
     prefer
    1.00
     organize
    0.99
    Act Density 0.314%

    No Known Activations