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

    Neuronpedia

    INDEX
    Explanations

    phrases related to cause and effect

    oai_token-act-pair · gpt-3.5-turbo

    statements indicating predictions, conditions, or important descriptions regarding various concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     runway
    -0.66
     floats
    -0.65
    luaj
    -0.63
     cones
    -0.62
     personalities
    -0.61
     plates
    -0.60
     Mi
    -0.60
     fuse
    -0.59
     trailers
    -0.58
     assassins
    -0.58
    POSITIVE LOGITS
     borne
    0.88
    antage
    0.82
     coupled
    0.78
     certainly
    0.77
    aiden
    0.77
     undoubtedly
    0.74
     exacerbated
    0.73
     aided
    0.73
     contrasted
    0.73
    ijing
    0.71
    Act Density 0.247%

    No Known Activations