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

    Neuronpedia

    INDEX
    Explanations

    arguments or reasons presented in a text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    AsUp
    -0.82
    Tikang
    -0.80
    featureID
    -0.75
    Tembelea
    -0.74
    BeginInit
    -0.72
    bootstrapcdn
    -0.70
    artifactId
    -0.66
    IBOutlet
    -0.66
    findpost
    -0.65
    complexContent
    -0.64
    POSITIVE LOGITS
     because
    1.28
    because
    1.13
     porque
    0.98
    Because
    0.93
     потому
    0.91
     perché
    0.89
     Because
    0.88
     omdat
    0.85
     karena
    0.82
     perchè
    0.81
    Act Density 0.436%

    No Known Activations