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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating purpose or intent

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     purposes
    -0.63
     Patro
    -0.61
     Gost
    -0.59
     šķ
    -0.56
     appea
    -0.54
     GIP
    -0.54
     Constantinople
    -0.53
     Anaconda
    -0.53
     Babylonian
    -0.52
     Yeti
    -0.52
    POSITIVE LOGITS
     виправивши
    0.92
     AssemblyCulture
    0.89
    <>();
    0.85
    :");
    0.84
    ".
    0.82
    "])
    0.82
    )";
    0.81
    :
    0.79
    fromnode
    0.79
     the
    0.78
    Act Density 0.357%

    No Known Activations