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

    Neuronpedia

    INDEX
    Explanations

    adjective-noun pairs where the adjective conveys a level of importance or significance to the noun

    oai_token-act-pair · gpt-3.5-turbo

    phrases that express indifference or the lack of importance regarding various topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    igslist
    -0.87
    uthor
    -0.86
    Cola
    -0.72
    soDeliveryDate
    -0.71
    åħī
    -0.71
    solete
    -0.71
    etheus
    -0.67
    LAN
    -0.67
    EVA
    -0.67
     guiActiveUn
    -0.67
    POSITIVE LOGITS
    ogie
    0.71
     cents
    0.68
     Cats
    0.66
     anymore
    0.66
    etheless
    0.63
     quality
    0.63
     GENERAL
    0.63
     LOVE
    0.61
     Subtle
    0.61
    ensity
    0.61
    Act Density 0.217%

    No Known Activations