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

    Neuronpedia

    INDEX
    Explanations

    concepts related to belief and reality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    RegressionTest
    -0.67
     chagrin
    -0.60
    GraphicsUnit
    -0.58
    IgnoreCase
    -0.57
     flamb
    -0.56
     dismay
    -0.56
     Align
    -0.56
     Longevity
    -0.55
     Diplomacy
    -0.54
     Legacy
    -0.53
    POSITIVE LOGITS
     constitutive
    0.66
     coordenadas
    0.61
     række
    0.59
     insofar
    0.56
    eficent
    0.56
    pozycji
    0.55
     rekke
    0.55
     bytu
    0.55
     captar
    0.55
     autón
    0.54
    Act Density 0.510%

    No Known Activations