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

    Neuronpedia

    INDEX
    Explanations

    mentions of different locations within the text

    oai_token-act-pair · gpt-3.5-turbo

    the word "this" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    letes
    -0.75
    ickets
    -0.74
    ques
    -0.72
    lete
    -0.72
    cks
    -0.71
    onto
    -0.70
     Izan
    -0.68
    onis
    -0.67
    rex
    -0.66
    stars
    -0.65
    POSITIVE LOGITS
     regard
    1.25
     context
    1.04
     vein
    1.03
     particular
    1.00
     vicinity
    0.98
     manner
    0.96
     circumstance
    0.89
     week
    0.89
     predicament
    0.87
     scenario
    0.86
    Act Density 0.056%

    No Known Activations