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

    Neuronpedia

    INDEX
    Explanations

    phrases related to positive outcomes or qualities

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "shine" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ionic
    -0.68
    went
    -0.65
    assian
    -0.65
    ilage
    -0.64
     Humans
    -0.62
    catentry
    -0.62
    urally
    -0.62
    artment
    -0.62
    tarian
    -0.61
    iev
    -0.61
    POSITIVE LOGITS
     shone
    1.12
     shine
    1.05
     shines
    1.03
     brightest
    0.98
     brighter
    0.93
     tremend
    0.91
     brightly
    0.88
     shining
    0.86
     forth
    0.84
    elight
    0.84
    Act Density 0.023%

    No Known Activations