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

    Neuronpedia

    INDEX
    Explanations

    instances of usage or references to figures and graphs within the document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arily
    -0.15
    nost
    -0.14
    ене
    -0.14
    anas
    -0.14
     drag
    -0.13
    elle
    -0.13
    oron
    -0.13
    rai
    -0.13
    ÑĢаб
    -0.13
     Lair
    -0.13
    POSITIVE LOGITS
    SSI
    0.16
    ipple
    0.15
     Brock
    0.15
    کر
    0.14
    uess
    0.14
    au
    0.14
    =explode
    0.14
     oma
    0.14
    ossa
    0.14
    iger
    0.14
    Act Density 0.006%

    No Known Activations