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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating emotional or personal experiences related to changes in environment or mindset

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     å·
    -0.07
    uish
    -0.07
    qua
    -0.07
    basePath
    -0.07
    oki
    -0.07
    icularly
    -0.07
    lya
    -0.06
     nữa
    -0.06
    .ribbon
    -0.06
    uib
    -0.06
    POSITIVE LOGITS
     hopes
    0.13
     plans
    0.12
     intentions
    0.12
     intention
    0.11
     intent
    0.11
     plan
    0.10
     expectations
    0.10
     intend
    0.10
     Intent
    0.09
     hope
    0.09
    Act Density 0.033%

    No Known Activations