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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating tendencies or inclinations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     VIAF
    -0.64
    EFIAPI
    -0.62
     Dominguez
    -0.57
    Portail
    -0.57
    hadiran
    -0.56
    impresa
    -0.54
     Warburton
    -0.54
    soul
    -0.53
     đức
    -0.53
    zerne
    -0.52
    POSITIVE LOGITS
     Tend
    1.17
    Tend
    1.17
     tends
    0.98
     tend
    0.93
     TEND
    0.88
     tending
    0.85
     tendency
    0.84
    RegressionTest
    0.84
    endencies
    0.84
     tendencies
    0.82
    Act Density 0.086%

    No Known Activations