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

    Neuronpedia

    INDEX
    Explanations

    words related to decisions or actions being taken in a specific context

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    umbnails
    -0.83
    */(
    -0.73
     partName
    -0.70
     Globe
    -0.68
    aughters
    -0.67
     Feast
    -0.67
     background
    -0.66
    illon
    -0.64
    ciating
    -0.64
     underscores
    -0.63
    POSITIVE LOGITS
     indeed
    1.09
     somehow
    1.07
    nt
    0.99
     actually
    0.92
     capable
    0.87
     viable
    0.84
     destined
    0.83
     acceptable
    0.83
     worthwhile
    0.82
     genuine
    0.81
    Act Density 2.216%

    No Known Activations