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

    Neuronpedia

    INDEX
    Explanations

    adjectives or adverbs indicating a change or disappearance

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the cessation of something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    urn
    -0.65
    iah
    -0.63
    aring
    -0.61
    esh
    -0.59
    gui
    -0.59
    emet
    -0.56
    rock
    -0.55
     Productions
    -0.55
    ela
    -0.55
    iani
    -0.54
    POSITIVE LOGITS
     longer
    3.66
     shorter
    2.33
     LONG
    1.81
     longest
    1.66
     taller
    1.51
     long
    1.50
     thicker
    1.49
     wider
    1.47
     leng
    1.42
     narrower
    1.40
    Act Density 0.018%

    No Known Activations