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

    Neuronpedia

    INDEX
    Explanations

    percentage values

    oai_token-act-pair · gpt-3.5-turbo

    percentage values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     moot
    -0.62
    long
    -0.55
     long
    -0.54
     motion
    -0.53
    sw
    -0.52
     extended
    -0.52
     oddly
    -0.51
    ower
    -0.51
     Storm
    -0.51
     comm
    -0.51
    POSITIVE LOGITS
    %,
    3.50
    %.
    2.82
    %;
    2.73
    %:
    2.55
    %),
    2.50
    %).
    2.37
    %)
    2.24
    %-
    2.23
    %"
    2.13
    %
    2.12
    Act Density 0.011%

    No Known Activations