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

    Neuronpedia

    INDEX
    Explanations

    words and phrases indicating actions, particularly focusing on states and transformations within texts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ñħод
    -0.17
    ifr
    -0.16
    edin
    -0.16
    ruba
    -0.15
    otec
    -0.15
    HECK
    -0.15
    edla
    -0.14
    íĩ´
    -0.14
     Böl
    -0.14
    haled
    -0.14
    POSITIVE LOGITS
    opic
    0.15
    ocol
    0.14
    uttle
    0.14
    uelle
    0.14
    atta
    0.14
    /renderer
    0.14
    佩
    0.13
     Blackburn
    0.13
     Shirley
    0.13
    uar
    0.13
    Act Density 0.021%

    No Known Activations