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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks at the end of sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    (!__
    -0.79
     CURIAM
    -0.74
     contextLoads
    -0.73
    antMatchers
    -0.73
    IndentedString
    -0.73
     MainAxisSize
    -0.72
    oneofs
    -0.72
     SafeMath
    -0.70
    accompag
    -0.68
    ImageContext
    -0.68
    POSITIVE LOGITS
     “
    0.64
     "
    0.63
     Wasn
    0.57
    featureID
    0.56
    
    0.55
    </i>
    0.53
    </h5>
    0.52
     Yeah
    0.52
    </em>
    0.52
     We
    0.51
    Act Density 0.048%

    No Known Activations