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

    Neuronpedia

    INDEX
    Explanations

    references to popular superhero franchises and their characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ptid
    -0.58
    ühm
    -0.55
    发表于
    -0.52
    omeness
    -0.51
    Kool
    -0.51
     Neat
    -0.50
    Brainz
    -0.50
    Personendaten
    -0.50
     dreapta
    -0.49
    SPJ
    -0.48
    POSITIVE LOGITS
     franchise
    0.73
    RetentionPolicy
    0.63
    ภาค
    0.63
    franchise
    0.61
    клопе
    0.61
     prequel
    0.59
     sequel
    0.57
     Franchise
    0.57
    StructEnd
    0.56
    XmlType
    0.56
    Act Density 0.157%

    No Known Activations