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

    Neuronpedia

    INDEX
    Explanations

    The neuron is looking for words that end in "-is" and are related to positive qualities or compliments

    oai_token-act-pair · gpt-3.5-turbo

    the verb "is" in various contexts, indicating assertions or states of being

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ¥ŀ
    -0.93
    è¦ļéĨĴ
    -0.78
    ¥µ
    -0.73
     ABE
    -0.71
     reconc
    -0.68
     crates
    -0.67
    ruciating
    -0.66
     thumbnail
    -0.66
     entrances
    -0.65
     manners
    -0.64
    POSITIVE LOGITS
    abeth
    1.25
    peed
    1.06
    earch
    1.02
    olate
    1.01
    cience
    0.95
    olation
    0.95
    aurus
    0.94
    pect
    0.90
    ciplinary
    0.90
    terness
    0.87
    Act Density 0.039%

    No Known Activations