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

    Neuronpedia

    INDEX
    Explanations

    mentions of items being created or designed

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "in" representing contexts or locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    idepress
    -0.72
    hur
    -0.70
    ivid
    -0.68
    norm
    -0.67
    etheless
    -0.67
     consumed
    -0.67
    uf
    -0.65
    rx
    -0.65
    channelAvailability
    -0.64
    worthy
    -0.64
    POSITIVE LOGITS
     conjunction
    1.25
     partnership
    1.23
     collaboration
    1.20
     secrecy
    1.09
     cooperation
    1.03
     accordance
    0.99
     haste
    0.98
     tandem
    0.94
     consultation
    0.91
     situ
    0.86
    Act Density 0.193%

    No Known Activations