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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate location or placement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ciz
    -0.18
    erre
    -0.15
     occasion
    -0.15
    irie
    -0.15
    quets
    -0.15
    .usermodel
    -0.15
    eri
    -0.15
    doi
    -0.14
    _rd
    -0.14
     place
    -0.14
    POSITIVE LOGITS
    olen
    0.14
    éĸī
    0.14
    umble
    0.14
    atu
    0.14
    kinson
    0.14
     Dale
    0.14
    endimento
    0.13
    tribution
    0.13
    SEA
    0.13
    igue
    0.13
    Act Density 0.043%

    No Known Activations