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

    Neuronpedia

    INDEX
    Explanations

    names of authors or contributors associated with academic publications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rowse
    -0.16
    obao
    -0.16
    orders
    -0.16
    ureau
    -0.15
    ideo
    -0.15
    aday
    -0.14
    allet
    -0.14
    ãĥ¼ãĥĭ
    -0.14
    ertino
    -0.14
    ella
    -0.14
    POSITIVE LOGITS
    onte
    0.17
    ENTA
    0.16
     bill
    0.16
    ifact
    0.15
    undo
    0.15
    ÏģÏį
    0.15
    opp
    0.15
    jo
    0.14
     multiplic
    0.14
     Bills
    0.13
    Act Density 0.084%

    No Known Activations