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

    Neuronpedia

    INDEX
    Explanations

    references to significant actions or events related to social or political topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    chalk
    -0.17
    rite
    -0.17
    alama
    -0.15
    InitialState
    -0.15
    ifo
    -0.15
    ystack
    -0.15
    osi
    -0.15
    .ship
    -0.14
     PURE
    -0.14
    iid
    -0.14
    POSITIVE LOGITS
    po
    0.17
    tracts
    0.15
    Å¡ak
    0.15
     se
    0.14
     ante
    0.14
    eneric
    0.14
    SF
    0.14
    èIJ½ãģ¡
    0.13
    ÄIJT
    0.13
     fant
    0.13
    Act Density 0.129%

    No Known Activations