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

    Neuronpedia

    INDEX
    Explanations

    text related to IP addresses and various GitHub repository details

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     gainera
    -0.54
     its
    -0.44
     pi
    -0.44
    ValuePair
    -0.44
    …
    -0.43
     so
    -0.42
     "
    -0.42
     or
    -0.42
     I
    -0.42
     and
    -0.41
    POSITIVE LOGITS
     Efq
    0.85
     Reſ
    0.82
     Houſe
    0.77
     Conſ
    0.76
    WireFormatLite
    0.75
     Cæsar
    0.74
     Majefty
    0.72
     Perſ
    0.72
     firebaseConfig
    0.72
     ſever
    0.71
    Act Density 0.077%

    No Known Activations