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

    Neuronpedia

    INDEX
    Explanations

    words related to extroversion and introversion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Nay
    -0.17
    arLayout
    -0.16
    hev
    -0.16
    uluk
    -0.16
    hti
    -0.15
    EXP
    -0.15
    utan
    -0.15
     Rip
    -0.14
    arias
    -0.14
    utf
    -0.14
    POSITIVE LOGITS
    ensive
    0.36
    remely
    0.34
    rem
    0.33
    reme
    0.30
    inction
    0.29
    ending
    0.28
    ortion
    0.27
    ensively
    0.27
    ensible
    0.26
    rema
    0.25
    Act Density 0.009%

    No Known Activations