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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate disclaimers or conditions of use

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     Efq
    -0.96
     Monfieur
    -0.93
     Majefty
    -0.88
     uſed
    -0.84
     Jefus
    -0.82
     doubtnut
    -0.82
     poffible
    -0.80
    BeginInit
    -0.79
     poffe
    -0.79
     itſelf
    -0.78
    POSITIVE LOGITS
    hasMoreElements
    0.59
    m
    0.50
    endphp
    0.47
     M
    0.46
    t
    0.43
    o
    0.42
    d
    0.41
     O
    0.41
    M
    0.41
     Car
    0.40
    Act Density 0.002%

    No Known Activations