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

    Neuronpedia

    INDEX
    Explanations

    negative sentiments expressed through derogatory terms

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

    poor quality crap

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    _
    -0.54
    geber
    -0.46
     ListTile
    -0.46
    }';
    -0.45
    '];
    -0.44
    ]));
    -0.44
    ListTile
    -0.44
    '");
    -0.44
     Goethe
    -0.43
     Esti
    -0.42
    POSITIVE LOGITS
     crap
    1.68
    crap
    1.34
    Crap
    1.23
     crappy
    0.94
     rubbish
    0.87
     stuff
    0.79
     junk
    0.75
     garbage
    0.71
    Tikang
    0.71
     STUFF
    0.71
    Act Density 0.002%

    No Known Activations