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

    Neuronpedia

    INDEX
    Explanations

    terms related to evaluation or judgment about people and events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     entanto
    -0.71
     Majefty
    -0.70
     videre
    -0.66
     Madura
    -0.66
     Efq
    -0.66
     reft
    -0.65
     Juf
    -0.65
     Cæsar
    -0.65
     blumen
    -0.63
     houſe
    -0.62
    POSITIVE LOGITS
    Parcelize
    0.73
    makeText
    0.70
     it
    0.66
    Rüyada
    0.65
    BeginContext
    0.65
    ondissement
    0.63
     him
    0.58
    فحة
    0.57
    xase
    0.57
     Label
    0.57
    Act Density 0.068%

    No Known Activations