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

    Neuronpedia

    INDEX
    Explanations

    phrases related to accidents and their consequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    unkt
    -0.16
    Ñİк
    -0.15
     haze
    -0.15
    ultipart
    -0.15
    .heap
    -0.14
    oyer
    -0.14
    wiki
    -0.14
     Raid
    -0.14
    ernals
    -0.14
    INED
    -0.14
    POSITIVE LOGITS
     unstable
    0.19
     plu
    0.17
     collapse
    0.17
    chl
    0.17
     leaning
    0.16
    -collapse
    0.16
     building
    0.16
    lef
    0.15
     collapses
    0.15
     coll
    0.15
    Act Density 0.037%

    No Known Activations