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

    Neuronpedia

    INDEX
    Explanations

    mentions of academic journals

    oai_token-act-pair · gpt-3.5-turbo

    the definite article "the" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     besides
    -0.75
    atics
    -0.71
     depended
    -0.70
     mutants
    -0.67
     withstand
    -0.67
     countered
    -0.66
    ampires
    -0.66
     beware
    -0.65
     survives
    -0.65
     safely
    -0.65
    POSITIVE LOGITS
     latter
    1.02
     aforementioned
    0.99
     latest
    0.97
     entirety
    0.92
     publication
    0.89
     outset
    0.89
     earliest
    0.87
     same
    0.87
    Journal
    0.86
     slightest
    0.81
    Act Density 0.652%

    No Known Activations