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

    Neuronpedia

    INDEX
    Explanations

    phrases or words that emphasize comparisons or similarities

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

    "as well as"

    np_acts-logits-general · gemini-2.0-flash

    as well as

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     stället
    -0.64
     Shakspeare
    -0.61
    R
    -0.61
    P
    -0.61
     Saltar
    -0.60
     anyway
    -0.59
     mesmas
    -0.58
    M
    -0.57
     wikipagina
    -0.57
     apesar
    -0.57
    POSITIVE LOGITS
     being
    1.19
     the
    1.08
     other
    1.06
     those
    1.05
     some
    1.02
     a
    0.91
     their
    0.90
     others
    0.90
     several
    0.89
     its
    0.88
    Act Density 0.106%

    No Known Activations