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

    Neuronpedia

    INDEX
    Explanations

    names of characters from the "Star Trek" series

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ahat
    -0.17
    kus
    -0.16
     maxHeight
    -0.15
    .embed
    -0.14
    δα
    -0.14
    HB
    -0.14
    rait
    -0.14
     Honda
    -0.14
    ascar
    -0.14
    StateManager
    -0.14
    POSITIVE LOGITS
     Enterprise
    0.41
     Trek
    0.38
     Star
    0.38
    Enterprise
    0.35
     Federation
    0.33
     Kling
    0.33
    Star
    0.32
     Pic
    0.30
     Kirk
    0.30
     enterprise
    0.29
    Act Density 0.064%

    No Known Activations