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

    Neuronpedia

    INDEX
    Explanations

    phrases that convey contrasts or conflicts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     valoración
    -0.41
     vectorielle
    -0.41
     juges
    -0.41
    userdetails
    -0.39
    ↵
    -0.39
     licorne
    -0.38
     solidaridad
    -0.38
     testigo
    -0.37
     unicornio
    -0.36
     Asegúrese
    -0.36
    POSITIVE LOGITS
    
    1.53
    
    1.51
    
    1.48
    
    1.46
    
    1.45
    
    1.44
    
    1.42
    
    1.42
    <0x17>
    1.36
    
    1.35
    Act Density 0.553%

    No Known Activations