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

    Neuronpedia

    INDEX
    Explanations

    technical terms and components related to security permissions and tokens

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    RegressionTest
    -0.73
     Савезне
    -0.53
    олові
    -0.49
    Попис
    -0.48
     Administrativna
    -0.47
    parsedMessage
    -0.46
    újo
    -0.46
     queſta
    -0.46
    ronpa
    -0.45
     ModelRenderer
    -0.45
    POSITIVE LOGITS
     PublicKey
    0.78
     Exteriores
    0.44
     juridiques
    0.44
     femininos
    0.42
    Források
    0.39
    EDEFAULT
    0.39
     MV
    0.38
     düşünü
    0.37
     sendok
    0.37
     masculinos
    0.36
    Act Density 0.017%

    No Known Activations