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

    Neuronpedia

    INDEX
    Explanations

    phrases related to personal experiences and emotional reflections

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

    Positive sentiment, often with intensifiers

    np_acts-logits-general · gemini-2.0-flash

    swear words and negative descriptors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     }],
    -0.77
     hiszen
    -0.68
     محفوظة
    -0.65
    DoubleQuotes
    -0.65
     />';
    -0.64
    ]-->
    -0.63
    />";
    -0.63
    //----
    -0.62
    "}\
    -0.62
    ++];
    -0.62
    POSITIVE LOGITS
     stupid
    1.07
     fucking
    1.05
     stupidly
    1.03
     goddamn
    1.01
     dumbass
    0.93
     freaking
    0.93
     idiot
    0.92
     shitty
    0.92
     annoying
    0.91
     FUCKING
    0.91
    Act Density 1.007%

    No Known Activations