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

    Neuronpedia

    INDEX
    Explanations

    phrases consisting of "in a" followed by an adjective and a noun

    oai_token-act-pair · gpt-3.5-turbo

    phrases that describe characteristics or qualities in a versatile context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ATURES
    -0.75
    AUD
    -0.67
    reon
    -0.66
    aints
    -0.66
    allion
    -0.65
    Extra
    -0.64
     icons
    -0.63
     Influence
    -0.62
    oola
    -0.62
    associated
    -0.62
    POSITIVE LOGITS
     nutshell
    1.49
     hurry
    1.36
     manner
    1.18
     heartbeat
    1.14
     pinch
    1.09
     timely
    1.02
     vacuum
    0.99
     variety
    0.88
     way
    0.86
     phased
    0.85
    Act Density 0.117%

    No Known Activations