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

    Neuronpedia

    INDEX
    Explanations

    conjunctions and prepositions indicating relationships between ideas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     betweenstory
    -0.87
     Савезне
    -0.80
    OGND
    -0.73
    RectangleBorder
    -0.68
    ugeot
    -0.68
    ]='\
    -0.66
    DockStyle
    -0.66
    DebuggerNonUser
    -0.65
    gorithm
    -0.63
     $_"
    -0.63
    POSITIVE LOGITS
     This
    0.52
    able
    0.50
    もの
    0.49
    ものを
    0.49
    ものが
    0.48
    pable
    0.48
    ju
    0.46
     
    0.46
     noirs
    0.46
    toBeTruthy
    0.45
    Act Density 0.388%

    No Known Activations