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

    Neuronpedia

    INDEX
    Explanations

    references to unions or group concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ########.
    -0.67
     statement
    -0.52
     poveznice
    -0.50
     statements
    -0.50
     suspend
    -0.47
     STATEMENTS
    -0.45
     saites
    -0.45
    addContainerGap
    -0.45
    ImageContext
    -0.44
     sniffing
    -0.43
    POSITIVE LOGITS
     union
    0.67
     chat
    0.63
    Chat
    0.61
     soul
    0.61
     Chat
    0.60
    soul
    0.60
    chat
    0.57
    
    0.55
    union
    0.54
    Union
    0.53
    Act Density 0.082%

    No Known Activations