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

    Neuronpedia

    INDEX
    Explanations

    negative sentiment and implications in the text

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

    entimental

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ↵
    -0.45
    …
    -0.40
     */
    -0.39
    s
    -0.39
    ↵↵
    -0.39
     …
    -0.39
     *
    -0.39
    ...
    -0.38
    ↵↵↵
    -0.37
     \
    -0.36
    POSITIVE LOGITS
     queſta
    1.03
    <unused8>
    1.02
    [@BOS@]
    1.01
    <unused14>
    1.01
    <unused43>
    1.01
    <unused51>
    1.01
    <unused42>
    1.01
    <unused41>
    1.01
    <unused16>
    1.01
    <unused28>
    1.01
    Act Density 0.024%

    No Known Activations