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

    Neuronpedia

    INDEX
    Explanations

    prepositions and contextual phrases indicating locations or positions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    upertino
    -0.16
    /dat
    -0.15
    iteDatabase
    -0.15
    istrovstvÃŃ
    -0.14
    (Collider
    -0.14
    ιβ
    -0.14
    issing
    -0.13
    alice
    -0.13
    urette
    -0.13
    ãĥ¼ãĤ¿
    -0.13
    POSITIVE LOGITS
    ÙĪÙĨÛĮ
    0.15
    ixed
    0.15
    emme
    0.15
    ic
    0.14
    isis
    0.14
    earer
    0.14
     Willis
    0.14
     Wend
    0.14
     Wide
    0.13
    ertas
    0.13
    Act Density 0.524%

    No Known Activations