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

    Neuronpedia

    INDEX
    Explanations

    assertions and expressions of belief or hope

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    AccessorTable
    -0.76
    
    -0.63
    AndEndTag
    -0.61
     InputDecoration
    -0.61
     ModelExpression
    -0.60
    EndInit
    -0.58
    SuppressMessage
    -0.56
     propOrder
    -0.55
    XtraReports
    -0.55
    httphttps
    -0.55
    POSITIVE LOGITS
     ativo
    0.71
     ordinaire
    0.63
     themselves
    0.63
     duquel
    0.60
     ourselves
    0.58
     attivo
    0.58
     himself
    0.57
     yourself
    0.57
     africaine
    0.56
     africain
    0.55
    Act Density 0.196%

    No Known Activations