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

    Neuronpedia

    INDEX
    Explanations

    references to authors and their contributions or viewpoints

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     CanadaChoose
    -0.58
    Autoritní
    -0.52
    Personensuche
    -0.50
     my
    -0.48
    Portale
    -0.46
     INTERESAR
    -0.44
     kors
    -0.44
     كومونز
    -0.44
     PRISON
    -0.43
    prison
    -0.42
    POSITIVE LOGITS
     informée
    0.47
     čierna
    0.43
     believes
    0.41
     supposes
    0.40
     escuchado
    0.39
    getMenuInflater
    0.39
     imagines
    0.38
    ThroughAttribute
    0.37
     thinks
    0.37
    SourceChecksum
    0.37
    Act Density 0.590%

    No Known Activations