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

    Neuronpedia

    INDEX
    Explanations

    references to locations or situations other than the current one

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "elsewhere."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aldi
    -0.72
    Moon
    -0.70
    alion
    -0.68
    oly
    -0.67
     sshd
    -0.66
    ony
    -0.66
    iasis
    -0.64
    rano
    -0.63
    =-=-=-=-=-=-=-=-
    -0.62
     Eclipse
    -0.62
    POSITIVE LOGITS
    abouts
    1.00
    worldly
    0.87
     describ
    0.85
     else
    0.75
    heric
    0.73
     Else
    0.71
    landish
    0.70
     abroad
    0.68
     inland
    0.68
    erent
    0.68
    Act Density 0.010%

    No Known Activations