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

    Neuronpedia

    INDEX
    Explanations

    terms that emphasize consideration, exclusion, and accounting for variables in analyses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    RegressionTest
    -0.55
     détour
    -0.53
     gynhyrchwyd
    -0.51
    complexContent
    -0.49
    opsida
    -0.48
     diplom
    -0.48
     mision
    -0.46
     dépla
    -0.45
    Personendaten
    -0.44
    پیوند
    -0.43
    POSITIVE LOGITS
     excluding
    1.18
     exclude
    1.14
     excludes
    1.06
     Exclude
    0.96
    excluding
    0.93
     excluded
    0.92
    Exclude
    0.85
    ględ
    0.84
     subtracting
    0.79
     omitting
    0.79
    Act Density 0.546%

    No Known Activations