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

    Neuronpedia

    INDEX
    Explanations

    verbs and phrases related to permission and entitlements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Locker
    -0.16
    boom
    -0.14
    /Branch
    -0.14
    ollar
    -0.14
    mercial
    -0.13
    ENE
    -0.13
     Recording
    -0.13
    EB
    -0.13
    xon
    -0.13
     @{
    -0.13
    POSITIVE LOGITS
    orer
    0.16
    sg
    0.15
     Circ
    0.15
    ноÑĪ
    0.15
     challenge
    0.15
    andr
    0.14
    è¶Ĭ
    0.14
     purs
    0.14
    open
    0.14
    ouver
    0.14
    Act Density 0.149%

    No Known Activations