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

    Neuronpedia

    INDEX
    Explanations

    phrases related to rights and permissions regarding content and policies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iefs
    -0.15
    ajas
    -0.14
    856
    -0.14
     repealed
    -0.14
    oley
    -0.14
    acier
    -0.14
    owied
    -0.14
    icial
    -0.13
    hit
    -0.13
    _asm
    -0.13
    POSITIVE LOGITS
     reserves
    0.22
     refuse
    0.18
     reserve
    0.18
    without
    0.17
    æĭĴ
    0.17
     refusal
    0.16
     actionTypes
    0.16
     without
    0.16
    jem
    0.16
     reserva
    0.16
    Act Density 0.032%

    No Known Activations