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

    Neuronpedia

    INDEX
    Explanations

    numerical references and structural components in procedural or technical descriptions

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    er
    -0.68
    ГЛА
    -0.68
     Conley
    -0.63
    ?!?
    -0.62
     Quig
    -0.61
    ெ
    -0.59
     Celeste
    -0.59
     I
    -0.57
     Mahoney
    -0.57
    ego
    -0.56
    POSITIVE LOGITS
    StructEnd
    0.83
    etheless
    0.79
    withstanding
    0.78
    ostante
    0.74
     eventdata
    0.73
     vVar
    0.73
    hloromethane
    0.71
    OrNil
    0.71
     "..\..\
    0.71
     Ivor
    0.68
    Act Density 0.012%

    No Known Activations