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

    Neuronpedia

    INDEX
    Explanations

    names or titles starting with the letter "G"

    oai_token-act-pair · gpt-3.5-turbo

    the character 'G' in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Rift
    -0.70
     Exile
    -0.61
     Conquest
    -0.60
     htt
    -0.60
     retrospect
    -0.59
     Earthqu
    -0.58
     derail
    -0.58
     sight
    -0.58
     divest
    -0.57
     timing
    -0.56
    POSITIVE LOGITS
    oliath
    1.25
    ourmet
    1.23
    ossip
    1.23
    reetings
    1.22
    irlfriend
    1.19
    reet
    1.18
    opher
    1.14
    wyn
    1.13
    ospels
    1.13
    eeks
    1.11
    Act Density 0.038%

    No Known Activations