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

    Neuronpedia

    INDEX
    Explanations

    expressions related to conflict and personal relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     and
    -0.17
     instead
    -0.17
     Dreams
    -0.15
    etCode
    -0.14
     well
    -0.14
    enal
    -0.14
     exaggerated
    -0.14
     educational
    -0.13
     exagger
    -0.13
     fair
    -0.13
    POSITIVE LOGITS
     risk
    0.21
     anymore
    0.19
    risk
    0.19
     Risk
    0.18
    Risk
    0.18
     risking
    0.17
    mere
    0.16
     potentially
    0.16
     risks
    0.16
     Ris
    0.15
    Act Density 0.249%

    No Known Activations