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

    Neuronpedia

    INDEX
    Explanations

    phrases that denote direct actions or relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    viewDidLoad
    -0.82
     animés
    -0.71
    MessageTagHelper
    -0.69
     Walkover
    -0.68
    algo
    -0.67
    RunWith
    -0.67
     Burrell
    -0.67
     HMM
    -0.67
     cuffs
    -0.67
     Packer
    -0.66
    POSITIVE LOGITS
     directly
    3.16
    directly
    2.95
     Directly
    2.90
     direct
    2.48
    Direct
    2.40
     DIRECT
    2.33
     directement
    2.32
    DIRECT
    2.28
     directamente
    2.24
    direct
    2.23
    Act Density 0.083%

    No Known Activations