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

    Neuronpedia

    INDEX
    Explanations

    terms and phrases related to optional elements or features

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     Strat
    -0.68
     Aten
    -0.59
    жнему
    -0.59
    arraycopy
    -0.58
     Trost
    -0.58
     strat
    -0.57
    办法
    -0.57
    Flynn
    -0.57
    Strat
    -0.56
    ed
    -0.55
    POSITIVE LOGITS
     Optional
    1.15
    optional
    1.13
    Optional
    1.12
     OPTIONAL
    1.05
     optional
    1.02
     betweenstory
    0.99
    OPTIONAL
    0.96
    IsOptional
    0.90
    opcional
    0.86
     opcional
    0.85
    Act Density 0.015%

    No Known Activations