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

    Neuronpedia

    INDEX
    Explanations

    references to awards and honors

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    SourceChecksum
    -0.61
     EconPapers
    -0.59
     verbonden
    -0.56
     jorden
    -0.56
     préfé
    -0.55
     étoient
    -0.54
     feroit
    -0.54
    Попис
    -0.54
     serez
    -0.53
    Abitanti
    -0.53
    POSITIVE LOGITS
     defaultstate
    0.61
     awards
    0.57
    ########.
    0.57
     accolades
    0.55
    ontale
    0.55
    Erstellt
    0.52
    SerializedName
    0.51
     Kem
    0.49
    ]$}
    0.48
    sozial
    0.47
    Act Density 0.011%

    No Known Activations