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

    Neuronpedia

    INDEX
    Explanations

    expressions related to opinions and assessments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Majefty
    -0.88
     consuls
    -0.86
     Chriftian
    -0.83
    Beijinhos
    -0.80
    ValueStyle
    -0.80
    Atentamente
    -0.79
     themſelves
    -0.79
     Monfieur
    -0.78
     Houſe
    -0.77
     Efq
    -0.77
    POSITIVE LOGITS
     its
    0.75
     it
    0.68
     It
    0.64
     easy
    0.62
     Its
    0.62
     snowing
    0.61
    Its
    0.59
    It
    0.59
    它
    0.59
     easier
    0.59
    Act Density 0.431%

    No Known Activations