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

    Neuronpedia

    INDEX
    Explanations

    prepositions or phrases indicating location or position

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    prepositions indicating location or origin

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     itſelf
    -0.66
     houſe
    -0.62
     Chriftian
    -0.60
     pleaſure
    -0.59
     fubject
    -0.59
     ſta
    -0.59
     fhew
    -0.58
     ſtate
    -0.58
     Majefty
    -0.58
     raiſ
    -0.58
    POSITIVE LOGITS
     Bedarf
    0.45
     **/
    0.43
    api
    0.43
    ئ
    0.43
     Bei
    0.43
    bei
    0.43
    ties
    0.42
     Gelegenheit
    0.42
     us
    0.42
    jší
    0.42
    Act Density 0.001%

    No Known Activations