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

    Neuronpedia

    INDEX
    Explanations

    references to tropical locations

    oai_token-act-pair · gpt-3.5-turbo

    references to "tropes" and related terminology in media and storytelling

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    yang
    -0.76
     imitation
    -0.73
     Darius
    -0.73
    elligence
    -0.68
    Berry
    -0.65
    Disk
    -0.65
    dk
    -0.64
    ongh
    -0.64
     leather
    -0.63
    urion
    -0.63
    POSITIVE LOGITS
     Trop
    3.31
    kees
    1.95
    trop
    1.90
     trop
    1.66
     tropes
    1.63
     trope
    1.57
     tid
    1.46
     eas
    1.19
    wik
    1.18
    pmwiki
    1.17
    Act Density 0.064%

    No Known Activations