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

    Neuronpedia

    INDEX
    Explanations

    prepositions and their function in conveying relationships between concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Qual
    -0.19
     cual
    -0.16
     Qual
    -0.16
    KS
    -0.15
     ki
    -0.15
    aliz
    -0.15
    opaque
    -0.15
    qual
    -0.14
    ieber
    -0.14
    qualification
    -0.14
    POSITIVE LOGITS
     wh
    0.28
     witch
    0.25
     whom
    0.24
     wb
    0.23
    wh
    0.23
     which
    0.20
    itch
    0.19
     w
    0.19
     Witch
    0.18
    lich
    0.18
    Act Density 0.060%

    No Known Activations