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

    Neuronpedia

    INDEX
    Explanations

    references to monetary contributions or donations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     
    -0.40
    ↵↵
    -0.35
    ↵
    -0.35
    NotEqualTo
    -0.34
     final
    -0.34
     ejus
    -0.32
    <bos>
    -0.31
     smart
    -0.29
     default
    -0.28
    The
    -0.28
    POSITIVE LOGITS
     Geſch
    0.99
     Geiſt
    0.91
     verified
    0.90
    <unused43>
    0.86
     Waſſer
    0.86
    <unused41>
    0.86
     zwiſchen
    0.86
    <unused17>
    0.85
    <unused3>
    0.85
    <pad>
    0.85
    Act Density 0.279%

    No Known Activations