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

    Neuronpedia

    INDEX
    Explanations

    mentions of uninhabited or unexplored places

    oai_token-act-pair · gpt-3.5-turbo

    terms related to uninhabited or unrecognized territories

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anwhile
    -0.93
    uyomi
    -0.78
    enegger
    -0.78
    */(
    -0.74
    orney
    -0.73
    ramid
    -0.68
    âĢ¢âĢ¢
    -0.68
     Seym
    -0.67
     hemor
    -0.67
     confir
    -0.66
    POSITIVE LOGITS
    itial
    1.24
    structed
    1.21
    jured
    1.16
    flation
    1.08
    cluded
    1.00
    verted
    1.00
    fect
    0.97
    formed
    0.97
    hibited
    0.97
    strument
    0.94
    Act Density 0.005%

    No Known Activations