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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions involving various parameters or functions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    <unused43>
    -1.54
    <unused41>
    -1.53
    <unused3>
    -1.52
    [@BOS@]
    -1.52
    <unused17>
    -1.52
    <unused74>
    -1.52
    <unused42>
    -1.52
    <unused51>
    -1.52
    <unused23>
    -1.52
    <pad>
    -1.52
    POSITIVE LOGITS
    </i>
    1.05
    ↵↵
    1.05
    </em>
    1.02
    </h3>
    0.92
    ↵
    0.88
    }}
    0.85
    </blockquote>
    0.82
     
    0.76
    ,
    0.73
    }
    0.73
    Act Density 0.480%

    No Known Activations