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

    Neuronpedia

    INDEX
    Explanations

    words related to conflict or controversy

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the substring "sp."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Masters
    -0.69
     Franz
    -0.68
     honour
    -0.67
    hyde
    -0.66
     Apprentice
    -0.66
    obyl
    -0.65
    hof
    -0.64
     STATES
    -0.64
     Halls
    -0.63
     Incarnation
    -0.63
    POSITIVE LOGITS
    ooky
    1.11
    atter
    1.09
    rawl
    1.09
    rit
    1.07
    atial
    1.06
    anish
    1.05
    ilt
    1.02
    ank
    1.01
    acer
    1.01
    anned
    1.00
    Act Density 0.017%

    No Known Activations