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

    Neuronpedia

    INDEX
    Explanations

    phrases or words indicating potential or likelihood of success or positive outcomes

    oai_token-act-pair · gpt-3.5-turbo

    references to something being promising or having potential

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    FactoryReloaded
    -0.81
    avia
    -0.80
    alach
    -0.77
    aida
    -0.76
    cation
    -0.75
    ento
    -0.73
    ophobia
    -0.72
    cart
    -0.71
    ocard
    -0.70
    otypes
    -0.70
    POSITIVE LOGITS
     promising
    1.08
     prospects
    0.83
    ly
    0.79
     promises
    0.78
     promise
    0.75
     cannabin
    0.72
     newcomer
    0.70
     youngsters
    0.68
     Gamble
    0.67
     strugg
    0.66
    Act Density 0.005%

    No Known Activations