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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating foundational or underlying principles for various topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     displacement
    -0.72
    Scu
    -0.72
     Ginn
    -0.71
    tighets
    -0.69
     Displacement
    -0.69
    ി
    -0.68
    displacement
    -0.68
     gug
    -0.67
     textView
    -0.66
     Scu
    -0.66
    POSITIVE LOGITS
     Based
    1.28
     based
    1.23
    Based
    1.22
    BASED
    1.22
    based
    1.19
     BASED
    1.16
     basé
    1.12
    bases
    1.00
     basée
    0.99
     Basing
    0.97
    Act Density 0.076%

    No Known Activations