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

    Neuronpedia

    INDEX
    Explanations

    sentences that convey personal commitment or experience

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ruc
    -0.18
    acom
    -0.15
    ohn
    -0.14
     Han
    -0.14
    onas
    -0.14
    ocus
    -0.14
    mare
    -0.14
    elligence
    -0.14
    iminal
    -0.14
    zet
    -0.14
    POSITIVE LOGITS
     exist
    0.19
     exists
    0.19
     existed
    0.19
     Cat
    0.18
     existe
    0.17
    ué
    0.15
    exists
    0.15
    fram
    0.15
    elo
    0.15
    Cat
    0.15
    Act Density 0.013%

    No Known Activations