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

    Neuronpedia

    INDEX
    Explanations

    phrases related to categorization or classification

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ģn
    -0.17
    421
    -0.16
    336
    -0.15
    ffa
    -0.15
    olley
    -0.15
    chem
    -0.14
    shares
    -0.14
    RuleContext
    -0.13
    æĢ§
    -0.13
    ến
    -0.13
    POSITIVE LOGITS
     ones
    0.17
    atoria
    0.15
     Ones
    0.15
     edm
    0.14
    obili
    0.14
    volt
    0.14
    jos
    0.14
     seamlessly
    0.14
     Ed
    0.14
    mos
    0.13
    Act Density 0.046%

    No Known Activations