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

    Neuronpedia

    INDEX
    Explanations

    prepositions indicating locations, directions, or movements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     editorial
    -0.14
    _COPY
    -0.14
     om
    -0.14
    istrat
    -0.14
    å°¼
    -0.13
    pell
    -0.13
    aln
    -0.13
    oms
    -0.13
     implementations
    -0.13
    ENCH
    -0.13
    POSITIVE LOGITS
     Repository
    0.17
    rud
    0.15
    -inverse
    0.15
    SENS
    0.15
     nues
    0.15
    loub
    0.14
    iggins
    0.14
     repositories
    0.14
    sep
    0.13
     gitti
    0.13
    Act Density 0.012%

    No Known Activations