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

    Neuronpedia

    INDEX
    Explanations

    instances of conflict or tension in relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     бÑĭло
    -0.19
     بÙĪدÙĨد
    -0.18
     Were
    -0.17
     бÑĭл
    -0.17
    Were
    -0.17
     бÑĭли
    -0.17
     بÙĪد
    -0.16
     byÅĤo
    -0.16
     бÑĭла
    -0.15
    peats
    -0.15
    POSITIVE LOGITS
     ate
    0.30
     got
    0.29
     took
    0.28
     sat
    0.27
     drank
    0.26
     threw
    0.26
     ran
    0.25
     drove
    0.25
    got
    0.24
     drew
    0.24
    Act Density 0.232%

    No Known Activations