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

    Neuronpedia

    INDEX
    Explanations

    expressions and phrases that describe subjective experiences or perceptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Similar
    -0.90
     Similar
    -0.84
     Kinds
    -0.84
    similar
    -0.82
    Kind
    -0.75
    Kinds
    -0.70
    kinds
    -0.69
     Types
    -0.69
    KIND
    -0.69
    Types
    -0.65
    POSITIVE LOGITS
     lenker
    0.57
    lipop
    0.54
     li
    0.52
    slidesToShow
    0.50
    matchCondition
    0.50
    ようになった
    0.49
    pinMode
    0.49
     liked
    0.49
    edan
    0.48
    ようになる
    0.48
    Act Density 0.125%

    No Known Activations