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

    Neuronpedia

    INDEX
    Explanations

    references to specific names or titles associated with individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ITOR
    -0.18
    peare
    -0.17
    adelphia
    -0.15
    ÙĪاÙĦ
    -0.15
    itive
    -0.15
    apper
    -0.14
     Tod
    -0.14
    traits
    -0.14
    EDA
    -0.14
    airy
    -0.14
    POSITIVE LOGITS
    iley
    0.20
    ground
    0.17
    room
    0.16
    lear
    0.15
    ile
    0.15
    autiful
    0.14
    azar
    0.14
    .debugLine
    0.14
    ixo
    0.14
    quets
    0.14
    Act Density 0.024%

    No Known Activations