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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating superiority or dominance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    elman
    -0.16
    chemas
    -0.16
    gis
    -0.15
    xea
    -0.14
    berger
    -0.14
    amik
    -0.14
    amination
    -0.14
    pio
    -0.14
     itemprop
    -0.14
    ngen
    -0.14
    POSITIVE LOGITS
     sensitivity
    0.20
     sensitive
    0.18
    jud
    0.17
     diamonds
    0.17
     anchor
    0.16
    y
    0.15
     gem
    0.15
     sensit
    0.15
     intolerance
    0.15
    FM
    0.15
    Act Density 0.004%

    No Known Activations