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

    Neuronpedia

    INDEX
    Explanations

    references to items, actions, and situations related to everyday life or experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Topics people discuss

    np_acts-logits-general · gemini-2.0-flash

    expressions of frustration or amusement

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     protoimpl
    -0.80
    "]);
    -0.74
    ">'+
    -0.71
    ."));
    -0.70
    DoubleQuotes
    -0.69
    ))}
    -0.68
    "]];
    -0.68
     erworben
    -0.67
    ']);
    -0.67
    "]));
    -0.66
    POSITIVE LOGITS
     because
    0.78
     lol
    0.77
     lmao
    0.76
     LOL
    0.76
     instead
    0.72
     dammit
    0.72
     porque
    0.70
     BECAUSE
    0.70
     LMAO
    0.70
     lmfao
    0.69
    Act Density 0.475%

    No Known Activations