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

    Neuronpedia

    INDEX
    Explanations

    second-person pronouns and phrases that address the reader directly

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    contentLoaded
    -0.72
     Accesat
    -0.64
    protoimpl
    -0.63
     oprot
    -0.62
    }());
    -0.61
     voici
    -0.60
     ſtate
    -0.60
     Conſ
    -0.59
     sudor
    -0.59
     Concerned
    -0.58
    POSITIVE LOGITS
     المعيارى
    0.54
     آدم
    0.52
     oneself
    0.51
     brand
    0.49
     itself
    0.49
    ешься
    0.47
     top
    0.46
    ByExample
    0.45
    Superficie
    0.45
     člověk
    0.45
    Act Density 0.137%

    No Known Activations