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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating ease or simplicity

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "easily" and its context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oft
    -0.75
    IAL
    -0.74
     Farmers
    -0.72
    mostly
    -0.68
     desperately
    -0.67
     Anthem
    -0.66
    yet
    -0.66
    raints
    -0.65
     strictly
    -0.64
     strongly
    -0.63
    POSITIVE LOGITS
     identifiable
    1.21
     accommod
    0.98
     recognizable
    0.98
     accessible
    0.93
     overlooked
    0.92
     achievable
    0.88
     readable
    0.87
     understandable
    0.87
     distinguish
    0.87
     attain
    0.86
    Act Density 0.040%

    No Known Activations