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

    Neuronpedia

    INDEX
    Explanations

    mathematical symbols and notations related to functions

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     Majefty
    -0.85
     itſelf
    -0.84
     Cæsar
    -0.83
     Theſe
    -0.82
     Monfieur
    -0.82
     Houſe
    -0.77
     myſelf
    -0.77
    ſelves
    -0.76
     Efq
    -0.76
     titolata
    -0.75
    POSITIVE LOGITS
     Real
    0.63
     real
    0.59
    illeur
    0.53
     trụ
    0.53
    <eos>
    0.52
     this
    0.52
     the
    0.52
     firm
    0.51
     T
    0.50
     if
    0.50
    Act Density 0.008%

    No Known Activations