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

    Neuronpedia

    INDEX
    Explanations

    patterns of conjunctions and prepositions in sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    et al

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Moscú
    -0.60
     Jerusalén
    -0.57
     gereja
    -0.55
     judíos
    -0.53
     Irán
    -0.53
     Autorin
    -0.52
     katholischen
    -0.52
     griega
    -0.52
     pinulongan
    -0.51
     pérd
    -0.50
    POSITIVE LOGITS
    %)$
    0.48
    $​
    0.47
    orice
    0.47
     ▲
    0.46
     XNUMX
    0.46
     ligiloj
    0.46
     ◄
    0.46
     Skyl
    0.45
     tolu
    0.45
    Bird
    0.44
    Act Density 0.014%

    No Known Activations