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

    Neuronpedia

    INDEX
    Explanations

    pronouns and references to specific groups of people

    oai_token-act-pair · gpt-3.5-turbo

    pronouns referring to collective experiences or group dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ¿½
    -0.75
    tains
    -0.71
     è£ıè¦ļéĨĴ
    -0.69
    opathy
    -0.69
    £ı
    -0.68
    ãĤ´ãĥ³
    -0.63
    Asset
    -0.61
     restructuring
    -0.59
     è£ıè
    -0.57
    antage
    -0.56
    POSITIVE LOGITS
    're
    1.75
    've
    1.34
     weren
    1.24
     aren
    1.20
     wanna
    1.11
     haven
    1.10
     are
    1.07
     were
    1.05
    'd
    1.04
    'll
    1.01
    Act Density 0.278%

    No Known Activations