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

    Neuronpedia

    INDEX
    Explanations

    tokens that signal the start of a new section or segment in a structured document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    хьтан
    -0.63
    Portale
    -0.62
     amp
    -0.61
     Yaman
    -0.60
    uller
    -0.57
    IVEREF
    -0.56
    uxley
    -0.56
    FileDescriptor
    -0.56
    NgModule
    -0.56
    ophenol
    -0.56
    POSITIVE LOGITS
    ."</
    0.85
    }")
    0.82
    '))
    0.76
     оригіналу
    0.76
    )}</
    0.75
    </
    0.74
    '</
    0.74
    </tr>
    0.73
     })}
    0.72
    }")]
    0.72
    Act Density 0.012%

    No Known Activations