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

    Neuronpedia

    INDEX
    Explanations

    causal relationships and descriptions of processes

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

    "[Verb] + by/through"

    np_acts-logits-general · gemini-2.0-flash

    means or cause

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     utafitiHapana
    -0.95
     myſelf
    -0.84
     Efq
    -0.77
    "])
    -0.76
    ']);
    -0.72
     himſelf
    -0.72
    ReusableCell
    -0.71
     perfons
    -0.71
    ']]
    -0.71
     Theſe
    -0.71
    POSITIVE LOGITS
     by
    0.82
     via
    0.66
     through
    0.61
    via
    0.59
     primarily
    0.55
     because
    0.52
    льность
    0.51
     roll
    0.51
     largely
    0.51
    roll
    0.51
    Act Density 0.662%

    No Known Activations