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

    Neuronpedia

    INDEX
    Explanations

    adjectives and verbs indicating change or progress

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the current state of affairs or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lees
    -0.79
    lication
    -0.78
    pora
    -0.74
    gdala
    -0.68
    ELD
    -0.68
    ¿½
    -0.67
    resents
    -0.66
    obook
    -0.65
    ois
    -0.64
    abulary
    -0.64
    POSITIVE LOGITS
     downhill
    0.93
     happening
    0.83
     spir
    0.80
     cov
    0.72
     transpired
    0.70
     happ
    0.70
     ju
    0.68
     stabilized
    0.67
     unravel
    0.66
     cryst
    0.66
    Act Density 0.159%

    No Known Activations