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

    Neuronpedia

    INDEX
    Explanations

    instances of disagreement or opposition in statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     AssemblyCulture
    -0.93
     متعلقه
    -0.89
    GEBURTSDATUM
    -0.86
    setVerticalGroup
    -0.85
     OFDb
    -0.84
    Personendaten
    -0.81
    TagMode
    -0.81
    ftagPool
    -0.81
     Roskov
    -0.81
    SourceChecksum
    -0.78
    POSITIVE LOGITS
     Sam
    0.54
     S
    0.48
     ar
    0.48
     Philip
    0.47
     t
    0.46
     sam
    0.46
    Sam
    0.45
     its
    0.44
     U
    0.44
     nu
    0.43
    Act Density 1.396%

    No Known Activations