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

    Neuronpedia

    INDEX
    Explanations

    technical terms and annotations in code or documentation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     --
    -0.64
     —
    -0.57
     [\
    -0.53
    --.
    -0.52
    --,
    -0.51
     ---
    -0.50
    ----
    -0.50
    —.
    -0.50
      (
    -0.50
     ----
    -0.50
    POSITIVE LOGITS
    "/>
    1.01
    ="+
    0.91
    awtextra
    0.87
    '/>
    0.73
    /'+
    0.69
     שוליים
    0.69
    }}/>
    0.68
    />
    0.66
    
    0.65
    /"+
    0.64
    Act Density 0.107%

    No Known Activations