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

    Neuronpedia

    INDEX
    Explanations

    references to letters or editorial contributions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     stop
    -0.49
     performing
    -0.48
    mist
    -0.47
     together
    -0.45
     master
    -0.44
     sur
    -0.44
    lax
    -0.43
     framework
    -0.42
     dentelle
    -0.42
     target
    -0.41
    POSITIVE LOGITS
    RegressionTest
    0.97
     שוליים
    0.89
    CloseOperation
    0.81
    Vidite
    0.79
    featureID
    0.77
    SourceChecksum
    0.77
    EDEFAULT
    0.77
    PhysRevLett
    0.75
     <",
    0.74
    Letters
    0.73
    Act Density 0.272%

    No Known Activations