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

    Neuronpedia

    INDEX
    Explanations

    references to the name "George."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     certain
    -0.19
    argas
    -0.18
    threshold
    -0.18
    Certain
    -0.17
    orca
    -0.16
    ORS
    -0.16
     thresholds
    -0.15
     threshold
    -0.15
    thew
    -0.15
    orda
    -0.15
    POSITIVE LOGITS
    aint
    0.18
    elts
    0.17
    anna
    0.16
    lbrace
    0.16
     Washington
    0.16
    olid
    0.16
    hausen
    0.16
    oj
    0.16
    urm
    0.16
     Orwell
    0.15
    Act Density 0.020%

    No Known Activations