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

    Neuronpedia

    INDEX
    Explanations

    prepositions indicating relationships or comparisons

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

    Following prepositions about various topics

    np_acts-logits-general · gemini-2.0-flash

    everything about

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    allenge
    -0.55
     dolay
    -0.54
    drawSprites
    -0.54
     "'");
    -0.53
    expandindo
    -0.52
    يكب
    -0.52
     ImportError
    -0.52
    akhstan
    -0.52
    IZONA
    -0.51
    melidir
    -0.51
    POSITIVE LOGITS
     everything
    1.15
     what
    1.06
     things
    1.02
    everything
    1.00
     EVERYTHING
    0.95
     anything
    0.94
     how
    0.89
     Everything
    0.87
    Everything
    0.86
     whats
    0.84
    Act Density 0.306%

    No Known Activations