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

    Neuronpedia

    INDEX
    Explanations

    variations of the word "end" in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    isible
    -0.17
     tslib
    -0.16
    /up
    -0.16
    xia
    -0.15
    inerary
    -0.15
     ResourceType
    -0.15
    illet
    -0.15
    ãģį
    -0.14
    lemetry
    -0.14
    away
    -0.14
    POSITIVE LOGITS
     wind
    0.23
     Wind
    0.21
    ow
    0.20
     up
    0.19
    Wind
    0.19
     wound
    0.19
     ended
    0.18
     Winds
    0.18
     upon
    0.17
    wind
    0.17
    Act Density 0.012%

    No Known Activations