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

    Neuronpedia

    INDEX
    Explanations

    references to violence and captivity in a historical or narrative context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     pun
    -0.16
    uppe
    -0.15
    zem
    -0.15
    ắm
    -0.14
     erg
    -0.14
     spat
    -0.14
    onis
    -0.14
    itom
    -0.14
     Olympus
    -0.14
     trip
    -0.14
    POSITIVE LOGITS
    hawks
    0.16
    apult
    0.15
     resil
    0.15
    iska
    0.14
     libertin
    0.14
    elder
    0.13
    ulence
    0.13
    ldr
    0.13
     Toolbox
    0.13
     trụ
    0.13
    Act Density 0.091%

    No Known Activations