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

    Neuronpedia

    INDEX
    Explanations

    references to consulting services and updates about projects or releases

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

    hyperlinks and call-to-action phrases that direct users to take specific actions like visiting websites, downloading apps, or signing up for services.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Negative Logits
    ?}
    -0.66
    }*/
    -0.65
    ？】
    -0.63
    }*/
    -0.62
    .)}
    -0.60
    )</
    -0.59
    ?\\
    -0.58
    .")]
    -0.58
     }}$}
    -0.57
    ;">
    -0.56
    POSITIVE LOGITS
    ↵↵
    0.74
    <eos>
    0.71
    </code>
    0.60
    </strong>
    0.57
    </b>
    0.55
    ”
    0.54
    “,
    0.54
    ֙
    0.51
    ↵
    0.51
    ↵↵↵↵
    0.48
    Act Density 0.491%

    No Known Activations