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

    Neuronpedia

    INDEX
    Explanations

    prepositions indicating location or association

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     hindsight
    -0.16
    ync
    -0.16
    okrat
    -0.16
     regards
    -0.15
    illez
    -0.15
    _observer
    -0.14
     increments
    -0.14
    is
    -0.14
    maal
    -0.14
    ites
    -0.14
    POSITIVE LOGITS
     consequence
    0.21
     behalf
    0.19
     token
    0.17
     leash
    0.15
    nection
    0.15
    mediately
    0.15
    ίο
    0.15
     видÑĥ
    0.15
     view
    0.15
    onth
    0.14
    Act Density 0.198%

    No Known Activations