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

    Neuronpedia

    INDEX
    Explanations

    boolean values indicating true or false states

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ""],
    -0.79
    ()));
    -0.79
    ']))
    -0.79
    ']],
    -0.78
    ']);
    -0.76
    '],
    -0.75
    ()]);
    -0.74
    '));
    -0.73
    "],
    -0.73
    '])){
    -0.73
    POSITIVE LOGITS
     disponibilités
    0.63
     מאוד
    0.52
     kasarigan
    0.52
     noires
    0.51
    False
    0.49
     graphiques
    0.49
     chevalier
    0.48
    BooleanField
    0.48
    brtc
    0.48
    Enough
    0.48
    Act Density 0.074%

    No Known Activations