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

    Neuronpedia

    INDEX
    Explanations

    terms related to preservation and its various forms

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     препратки
    -0.86
    genstein
    -0.82
     Walling
    -0.74
    AccessorTable
    -0.74
     impra
    -0.73
    FormTagHelper
    -0.73
    Juven
    -0.71
    SequentialGroup
    -0.70
    ränkt
    -0.70
    +#+#
    -0.69
    POSITIVE LOGITS
    Preserve
    1.20
     Preserve
    1.19
     preserve
    1.15
     Preservation
    1.08
    preserve
    1.06
     preserved
    1.05
     PRESERV
    1.03
     preserves
    1.00
     preservation
    0.98
     preserving
    0.93
    Act Density 0.007%

    No Known Activations