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

    Neuronpedia

    INDEX
    Explanations

    words related to specific names and titles, especially those not commonly used

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     Werewolf
    -0.71
     guiActiveUnfocused
    -0.71
     Algeria
    -0.67
     Metatron
    -0.66
     Blazers
    -0.65
     Boko
    -0.64
     Borg
    -0.63
     Olympia
    -0.61
     Marse
    -0.61
     4096
    -0.60
    POSITIVE LOGITS
    iting
    1.46
    its
    1.46
    itor
    1.39
    itors
    1.36
    ited
    1.34
    icial
    1.19
    itt
    1.17
    itures
    1.15
    itions
    1.15
    icion
    1.11
    Act Density 0.048%

    No Known Activations