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

    Neuronpedia

    INDEX
    Explanations

    references to accountability and transparency in actions and decisions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     olm
    -0.17
     Edison
    -0.16
    ich
    -0.15
     Dunn
    -0.15
    edImage
    -0.15
    ylon
    -0.14
    ãģ
    -0.14
     Sparks
    -0.14
    tics
    -0.14
     оконÑĩ
    -0.14
    POSITIVE LOGITS
    ãģŁãģĹ
    0.16
     plenty
    0.15
    å¿Ĺ
    0.15
    mada
    0.14
    oded
    0.14
    kos
    0.14
     баÑĢ
    0.14
    ussen
    0.14
     Cousins
    0.14
    Already
    0.13
    Act Density 0.295%

    No Known Activations