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

    Neuronpedia

    INDEX
    Explanations

    abbreviations or special terms related to classifications or categories

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    ('/:
    -0.90
    ("/:
    -0.68
    Ronnie
    -0.67
     Dunlap
    -0.67
     Dietz
    -0.66
     “
    -0.65
     resina
    -0.65
    y
    -0.62
    ><!--
    -0.61
    ade
    -0.61
    POSITIVE LOGITS
     xs
    1.59
     XS
    1.41
    xs
    1.36
    XS
    1.05
     myſelf
    1.02
    styleType
    1.01
     Majefty
    0.99
     Monfieur
    0.96
     Chriftian
    0.94
     themſelves
    0.90
    Act Density 0.001%

    No Known Activations