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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating transitions or shifts in the narrative

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arrants
    -0.17
    abei
    -0.15
    ucht
    -0.14
    ¦
    -0.14
    wyn
    -0.13
    plx
    -0.13
    oulos
    -0.13
    ire
    -0.13
    ault
    -0.13
    reet
    -0.13
    POSITIVE LOGITS
    POSITE
    0.15
    -ring
    0.14
    ¶Į
    0.14
    ALSE
    0.14
     ring
    0.13
     valign
    0.13
     Ring
    0.13
     exit
    0.13
     rings
    0.13
    alse
    0.13
    Act Density 0.041%

    No Known Activations