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

    Neuronpedia

    INDEX
    Explanations

    references to authority and hierarchy in relationships

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    NameInMap
    -0.65
    DockStyle
    -0.63
    发表于
    -0.53
    ellees
    -0.52
    Enllaces
    -0.51
    ValueStyle
    -0.51
    enged
    -0.49
    Izvori
    -0.49
     invokingState
    -0.48
    dymyr
    -0.47
    POSITIVE LOGITS
     quæ
    0.67
     Efq
    0.66
     Majefty
    0.66
     raiſ
    0.65
     auffi
    0.63
     Shakspeare
    0.62
     Monfieur
    0.61
    ſelf
    0.60
     Jefus
    0.60
     fathoms
    0.60
    Act Density 0.123%

    No Known Activations