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

    Neuronpedia

    INDEX
    Explanations

    words related to wilderness or the natural environment

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "wild" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Acceler
    -0.77
    istries
    -0.75
     Issue
    -0.74
    heed
    -0.73
    assium
    -0.67
     unfocusedRange
    -0.67
     Reson
    -0.66
    itus
    -0.66
     Vide
    -0.66
     Physics
    -0.65
    POSITIVE LOGITS
     wild
    3.63
    wild
    2.50
    Wild
    2.05
     Wild
    2.01
     feral
    1.52
     crazy
    1.29
     wilderness
    1.28
     tame
    1.25
     nuts
    1.23
     wolves
    1.15
    Act Density 0.013%

    No Known Activations