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

    Neuronpedia

    INDEX
    Explanations

    expressions of realization or surprise

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oard
    -0.18
    ienie
    -0.17
    evice
    -0.16
    eros
    -0.16
    ical
    -0.15
    incare
    -0.15
    ural
    -0.15
    indr
    -0.14
    een
    -0.14
    inent
    -0.14
    POSITIVE LOGITS
    318
    0.16
     reel
    0.15
    es
    0.15
    /welcome
    0.15
     rem
    0.15
     Ree
    0.15
     Movement
    0.14
     boy
    0.14
    rem
    0.14
    itters
    0.14
    Act Density 0.040%

    No Known Activations