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

    Neuronpedia

    INDEX
    Explanations

    relations regarding measurement and evaluation of performance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     sério
    -0.63
     legitimately
    -0.61
     skuto
    -0.61
    真正
    -0.58
     essenciais
    -0.58
     irl
    -0.58
     genuinely
    -0.58
    Personendaten
    -0.58
     véritables
    -0.57
     véritable
    -0.57
    POSITIVE LOGITS
     superfic
    0.73
     rigidly
    0.72
     rote
    0.72
     rigid
    0.71
     blindly
    0.71
     superficial
    0.68
     flashy
    0.66
     silo
    0.65
     regurg
    0.65
     cookie
    0.63
    Act Density 0.721%

    No Known Activations