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

    Neuronpedia

    INDEX
    Explanations

    names and titles of individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Strafe
    -0.73
    wahati
    -0.70
     COD
    -0.70
    basicConfig
    -0.68
    ówno
    -0.67
    =()
    -0.67
     Koch
    -0.66
    setVerticalGroup
    -0.64
     colo
    -0.62
    setCode
    -0.61
    POSITIVE LOGITS
     Mr
    2.13
    Mr
    2.05
     mr
    1.64
     Mrs
    1.46
     Mister
    1.41
    Mrs
    1.41
     Ms
    1.39
    mr
    1.32
    Mister
    1.27
     MR
    1.27
    Act Density 0.055%

    No Known Activations