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

    Neuronpedia

    INDEX
    Explanations

    words related to careful examination or assessment

    oai_token-act-pair · gpt-3.5-turbo

    terms related to evaluation and prioritization of actions or subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    æĸ¹
    -0.74
    RESULTS
    -0.73
    avorite
    -0.70
    BACK
    -0.68
    VIDEO
    -0.66
     DRAG
    -0.65
    GROUND
    -0.64
     Huck
    -0.63
    HOME
    -0.62
     blindly
    -0.61
    POSITIVE LOGITS
    izing
    2.00
    izers
    1.95
    ization
    1.93
    ised
    1.92
    ized
    1.91
    ising
    1.90
    izations
    1.87
    isers
    1.86
    isation
    1.73
    izes
    1.73
    Act Density 0.071%

    No Known Activations