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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating personal opinions or subjective evaluations

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    OGND
    -1.09
     protoimpl
    -0.89
     препратки
    -0.84
     myſelf
    -0.83
     RISERV
    -0.79
    SequentialGroup
    -0.78
    RegistryLite
    -0.78
    DockStyle
    -0.77
    تقاوى
    -0.77
     Roskov
    -0.77
    POSITIVE LOGITS
     Red
    0.51
     b
    0.50
     L
    0.46
     an
    0.44
     com
    0.43
    …
    0.40
    INERY
    0.40
     B
    0.40
     old
    0.40
     Com
    0.40
    Act Density 0.816%

    No Known Activations