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

    Neuronpedia

    INDEX
    Explanations

    significant events or themes highlighted in a discussion or text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    á»ĵ
    -0.15
    ERING
    -0.15
    ationale
    -0.15
    znik
    -0.14
    acd
    -0.14
    \Entities
    -0.14
     @}
    -0.14
    ushman
    -0.14
    reme
    -0.14
    леж
    -0.14
    POSITIVE LOGITS
     begging
    0.16
     hostage
    0.15
     Pit
    0.14
     spis
    0.14
    olis
    0.14
     begged
    0.14
    aty
    0.14
    èģ
    0.14
     whence
    0.13
     Governors
    0.13
    Act Density 0.120%

    No Known Activations