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

    Neuronpedia

    INDEX
    Explanations

    phrases related to technology and computation

    oai_token-act-pair · gpt-3.5-turbo

    references to systems and their capabilities, particularly in the context of technology and regulations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Closure
    -0.75
    OTOS
    -0.71
    Dash
    -0.69
    女
    -0.69
    mir
    -0.68
    inho
    -0.66
     Cheong
    -0.65
    ItemThumbnailImage
    -0.64
    ãĥ¢
    -0.63
    manuel
    -0.62
    POSITIVE LOGITS
     outdoors
    0.82
     (>
    0.76
    ktop
    0.75
    iaries
    0.75
     deficient
    0.74
     unlucky
    0.73
     prone
    0.73
     improperly
    0.71
     subscribers
    0.70
     sensitive
    0.70
    Act Density 0.873%

    No Known Activations