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

    Neuronpedia

    INDEX
    Explanations

    phrases that describe characteristics or attributes

    oai_token-act-pair · gpt-3.5-turbo

    the verb "are" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    west
    -0.89
    luaj
    -0.83
    isine
    -0.75
    culosis
    -0.74
    ONSORED
    -0.72
    090
    -0.69
    dt
    -0.68
    \\\\\\\\
    -0.68
    aye
    -0.67
    evaluate
    -0.66
    POSITIVE LOGITS
     notoriously
    1.21
     typically
    1.07
     inherently
    1.04
     plentiful
    1.02
     symbols
    1.02
     relics
    1.00
     magnets
    1.00
     prolifer
    1.00
     ubiquitous
    1.00
     everywhere
    1.00
    Act Density 0.188%

    No Known Activations