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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating the absence or lack of something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Various
    -0.23
     Numerous
    -0.19
    Various
    -0.18
    patrick
    -0.16
     various
    -0.15
     Things
    -0.15
     Most
    -0.15
    rape
    -0.14
    most
    -0.14
     whatever
    -0.14
    POSITIVE LOGITS
    thin
    0.36
    -one
    0.35
    xious
    0.32
    things
    0.28
    isy
    0.28
     longer
    0.27
    one
    0.26
     discern
    0.26
     further
    0.25
    ël
    0.25
    Act Density 0.117%

    No Known Activations