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

    Neuronpedia

    INDEX
    Explanations

    phrases related to reasons or purposes

    oai_token-act-pair · gpt-3.5-turbo

    terms related to legality and reasons associated with medical and political contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    xon
    -0.71
    onet
    -0.66
    etheless
    -0.63
    former
    -0.61
    atars
    -0.61
    dB
    -0.60
    ilant
    -0.58
     beaten
    -0.57
    gall
    -0.57
    flat
    -0.57
    POSITIVE LOGITS
     purposes
    2.52
     reasons
    2.11
     sake
    2.07
     purpose
    1.79
     reason
    1.51
     Reasons
    1.35
    purpose
    1.18
     Purpose
    1.15
    ummies
    1.10
     convenience
    1.00
    Act Density 0.580%

    No Known Activations