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

    Neuronpedia

    INDEX
    Explanations

    structured legal terminology and references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ProtoMessage
    -1.23
    httphttps
    -1.19
     ſind
    -1.19
     queſta
    -1.16
    AndEndTag
    -1.13
     MainAxisSize
    -1.12
    <unused68>
    -1.11
    <unused52>
    -1.11
    [@BOS@]
    -1.11
    <pad>
    -1.10
    POSITIVE LOGITS
    ↵↵
    2.08
    ↵
    0.94
    <eos>
    0.79
    ↵↵↵
    0.47
    ↵↵↵↵
    0.41
        
    0.34
      
    0.33
    0.33
       
    0.31
    	
    0.31
    Act Density 0.937%
    No Known Activations