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

    Neuronpedia

    INDEX
    Explanations

    mentions of specific locations or names related to a person or organization

    oai_token-act-pair · gpt-3.5-turbo

    statements related to existence and identity, particularly the use of the verb "to be."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ipeg
    -0.71
     Anniversary
    -0.70
     Deaths
    -0.68
     expire
    -0.66
     IDs
    -0.66
     showc
    -0.65
    uld
    -0.65
    eor
    -0.65
     Rankings
    -0.65
     Landing
    -0.64
    POSITIVE LOGITS
     fascinated
    1.53
     obsessed
    1.40
     wary
    1.35
     interested
    1.35
     keen
    1.33
     intrigued
    1.32
     reluctant
    1.31
     hesitant
    1.29
     skeptical
    1.27
     aware
    1.27
    Act Density 0.366%

    No Known Activations