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

    Neuronpedia

    INDEX
    Explanations

    terms related to facilities or accessibility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    icamente
    -0.16
    een
    -0.16
    eper
    -0.15
    ear
    -0.15
    eenth
    -0.15
    ight
    -0.14
    ees
    -0.14
    ez
    -0.14
    Ctrls
    -0.14
    ÑĢип
    -0.14
    POSITIVE LOGITS
    ult
    0.27
    ilitation
    0.27
    ilit
    0.26
     fac
    0.25
    fac
    0.25
    ilitating
    0.24
     Fac
    0.23
    ilities
    0.23
    Fac
    0.21
    ILITY
    0.21
    Act Density 0.010%

    No Known Activations