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

    Neuronpedia

    INDEX
    Explanations

    comparative phrases related to effectiveness and performance

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

    Comparison or similarity

    np_acts-logits-general · gemini-2.0-flash

    comparisons and similarities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    SequentialGroup
    -0.54
    extra
    -0.53
    this
    -0.50
     Different
    -0.49
     additional
    -0.47
     Empieza
    -0.47
    different
    -0.46
    Different
    -0.46
    new
    -0.46
    randrange
    -0.46
    POSITIVE LOGITS
     counterparts
    1.17
     comparable
    1.15
     equivalently
    1.00
     similarly
    0.98
     counterpart
    0.98
    lihood
    0.97
     similares
    0.96
     equivalent
    0.96
     analogous
    0.94
     similar
    0.94
    Act Density 0.740%

    No Known Activations