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

    Neuronpedia

    INDEX
    Explanations

    actions related to doing tasks or achieving goals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     betweenstory
    -0.96
    IntoConstraints
    -0.81
    ChildScrollView
    -0.76
     tartalomajánló
    -0.73
    بوابة
    -0.71
    parsedMessage
    -0.70
     surla
    -0.69
     Ise
    -0.69
     <<<<<<<<<<<<<<
    -0.68
    ImageContext
    -0.67
    POSITIVE LOGITS
     Do
    0.70
     do
    0.69
    Do
    0.66
     a
    0.65
     nothing
    0.64
     work
    0.64
     away
    0.62
     anything
    0.62
     it
    0.59
     something
    0.59
    Act Density 0.124%

    No Known Activations