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

    Neuronpedia

    INDEX
    Explanations

    unique or specialized characters or symbols in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     organis
    -0.14
    ivant
    -0.14
    nek
    -0.13
     SplashScreen
    -0.13
    erer
    -0.13
     Andersen
    -0.13
    aper
    -0.13
     organising
    -0.13
     favourable
    -0.13
    sted
    -0.13
    POSITIVE LOGITS
     prep
    0.21
     audition
    0.20
     preparation
    0.20
     rehearsal
    0.20
     Prep
    0.19
     research
    0.19
     inhab
    0.18
     prepared
    0.18
     rehears
    0.18
     prepar
    0.18
    Act Density 0.006%

    No Known Activations