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

    Neuronpedia

    INDEX
    Explanations

    references to complex procedures and and their implications

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

    sequence or list conjunctions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     
    -0.40
     by
    -0.28
     usually
    -0.27
      
    -0.27
     he
    -0.26
     following
    -0.26
     I
    -0.26
    d
    -0.26
     they
    -0.26
     with
    -0.26
    POSITIVE LOGITS
    LookAnd
    1.04
    <unused41>
    0.99
    <unused74>
    0.98
    [@BOS@]
    0.98
    <unused28>
    0.98
    <unused47>
    0.98
    <unused51>
    0.98
    <unused17>
    0.98
    <unused3>
    0.98
    <unused8>
    0.98
    Act Density 0.207%

    No Known Activations