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

    Neuronpedia

    INDEX
    Explanations

    indicators of approval ratings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     â
    -0.14
    aram
    -0.14
     Güven
    -0.14
    atta
    -0.13
    lot
    -0.13
    âĢ¦
    -0.13
    atomy
    -0.13
    ahn
    -0.13
     alike
    -0.12
    ou
    -0.12
    POSITIVE LOGITS
    تز
    0.17
    _DEPRECATED
    0.14
    #End
    0.14
     Fle
    0.14
     podrob
    0.14
    (tol
    0.14
    AndView
    0.13
    _UNUSED
    0.13
    aylight
    0.13
    ORY
    0.13
    Act Density 0.291%

    No Known Activations