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

    Neuronpedia

    INDEX
    Explanations

    prepositions and their varying strengths in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    okud
    -0.15
    edef
    -0.15
    _exempt
    -0.15
    edom
    -0.15
    oval
    -0.15
    è¨
    -0.15
    EndPoint
    -0.15
    avery
    -0.14
    iones
    -0.14
    arges
    -0.14
    POSITIVE LOGITS
    wards
    0.16
    aman
    0.16
    owie
    0.15
    asar
    0.14
     Dro
    0.14
    ith
    0.14
    olt
    0.14
    aku
    0.13
    -central
    0.13
     s
    0.13
    Act Density 0.177%

    No Known Activations