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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate conditions or premises for reasoning or conclusions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     displacement
    -0.73
     Displacement
    -0.71
     Ginn
    -0.71
     Waller
    -0.70
    displacement
    -0.70
     Walters
    -0.70
    ి
    -0.68
     gug
    -0.67
     textView
    -0.67
     Flanagan
    -0.66
    POSITIVE LOGITS
    Based
    1.38
     Based
    1.36
     based
    1.35
    BASED
    1.35
    based
    1.34
     BASED
    1.27
     basé
    1.17
     basée
    1.08
     basado
    1.03
    bases
    1.02
    Act Density 0.087%

    No Known Activations