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

    Neuronpedia

    INDEX
    Explanations

    prepositions indicating spatial or temporal relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    üz
    -0.17
    _blob
    -0.15
    _almost
    -0.15
    arf
    -0.14
    uzu
    -0.14
    onya
    -0.14
    porto
    -0.14
    ÏĢιÏĥ
    -0.14
    .stamp
    -0.14
     meisjes
    -0.14
    POSITIVE LOGITS
     odds
    0.28
     fault
    0.24
     risk
    0.23
     advantage
    0.22
    witter
    0.22
     ease
    0.21
     pains
    0.21
     logger
    0.20
     peace
    0.20
     liberty
    0.20
    Act Density 0.042%

    No Known Activations