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

    Neuronpedia

    INDEX
    Explanations

    references to victory or related terms

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    </b>
    -0.75
    lr
    -0.63
    wn
    -0.61
    </i>
    -0.61
    am
    -0.59
    app
    -0.59
    dfrac
    -0.57
     Sean
    -0.57
    pp
    -0.56
    sam
    -0.56
    POSITIVE LOGITS
     Vict
    1.27
     VICT
    1.18
    Vict
    1.13
     Victory
    1.08
     VICTOR
    1.04
     victoria
    1.01
    vict
    1.01
     victor
    1.00
     Victor
    0.97
     propOrder
    0.96
    Act Density 0.010%

    No Known Activations