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

    Neuronpedia

    INDEX
    Explanations

    frequent and significant conjunctions and prepositions in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    illas
    -0.15
    Fund
    -0.15
    edImage
    -0.14
     commune
    -0.14
    ãĤ·ãĤ¢
    -0.14
     Ere
    -0.14
    awl
    -0.14
     yok
    -0.13
    ersed
    -0.13
    _fwd
    -0.13
    POSITIVE LOGITS
     Central
    0.15
    ennon
    0.14
    /token
    0.14
     Gray
    0.14
     ActionTypes
    0.14
    rieb
    0.14
    nej
    0.13
    erto
    0.13
     centralized
    0.13
    ayment
    0.13
    Act Density 0.001%

    No Known Activations