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

    Neuronpedia

    INDEX
    Explanations

    code snippets or technical discussions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     exerc
    -0.76
     Rav
    -0.69
     Mellon
    -0.68
    andowski
    -0.64
    ITED
    -0.63
    issued
    -0.62
     Nau
    -0.61
     Aviv
    -0.60
     kne
    -0.59
    ocamp
    -0.59
    POSITIVE LOGITS
    %%%%
    1.01
    reet
    0.88
    AppData
    0.84
    loop
    0.81
    -+
    0.80
    files
    0.78
    ennial
    0.77
    ername
    0.75
    »
    0.74
    FREE
    0.74
    Act Density 0.047%

    No Known Activations