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

    Neuronpedia

    INDEX
    Explanations

    instances of criticism or assessment of performance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ificio
    -0.17
    svp
    -0.15
     actually
    -0.15
     reform
    -0.14
    vincia
    -0.14
    ekli
    -0.14
     Tories
    -0.14
     reforms
    -0.14
     Reform
    -0.14
    acie
    -0.14
    POSITIVE LOGITS
    ric
    0.16
    plural
    0.14
    AMI
    0.14
     ÙħاÙĦ
    0.14
    oeff
    0.14
    ITO
    0.14
    cac
    0.14
    ONSE
    0.14
    lev
    0.14
     dressing
    0.14
    Act Density 0.010%

    No Known Activations