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

    Neuronpedia

    INDEX
    Explanations

    specific patterns or terms related to specific variables in a structured or experimental context

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     faſt
    -0.86
    windowFixed
    -0.84
     Efq
    -0.83
     houſe
    -0.79
    thâu
    -0.77
     Houſe
    -0.77
     purpoſe
    -0.77
     Jefus
    -0.77
     ſever
    -0.74
     ſta
    -0.74
    POSITIVE LOGITS
    SequentialGroup
    0.58
    Vidite
    0.54
    Datuak
    0.52
     all
    0.52
     …
    0.49
     the
    0.48
     […]
    0.48
     l
    0.46
     he
    0.46
     data
    0.46
    Act Density 0.001%

    No Known Activations