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

    Neuronpedia

    INDEX
    Explanations

    the name "Shorten" either in full or partially

    oai_token-act-pair · gpt-3.5-turbo

    instances of the name "Short" referenced in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ILLE
    -0.91
    itational
    -0.90
    igators
    -0.78
    risome
    -0.77
    ICAN
    -0.72
    ILA
    -0.68
    vironment
    -0.67
    iances
    -0.66
    VERTIS
    -0.65
    Magikarp
    -0.64
    POSITIVE LOGITS
    ened
    1.03
    cuts
    1.00
    comings
    0.98
    short
    0.90
    cut
    0.89
    ness
    0.81
    bread
    0.81
     Term
    0.80
    casts
    0.79
    ening
    0.79
    Act Density 0.014%

    No Known Activations