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

    Neuronpedia

    INDEX
    Explanations

    prepositions related to support or reason

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     mikina
    -0.76
     XJ
    -0.74
    ..\..\
    -0.73
     nødven
    -0.68
     arbejds
    -0.68
     mercan
    -0.67
    Sche
    -0.66
     Jacobi
    -0.65
     Calabria
    -0.65
    ătă
    -0.63
    POSITIVE LOGITS
     FOR
    1.65
    FOR
    1.50
     For
    1.49
     for
    1.38
    For
    1.34
    for
    1.33
     für
    1.19
    Για
    1.11
     voor
    1.09
    ForValue
    1.08
    Act Density 0.541%

    No Known Activations