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

    Neuronpedia

    INDEX
    Explanations

    words and phrases related to segmentation and classification

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     pleaſure
    -1.14
     Anſ
    -1.03
     Reſ
    -1.01
     itſelf
    -0.99
     Diſ
    -0.98
     Houſe
    -0.96
     raiſ
    -0.95
     themſelves
    -0.94
     Theſe
    -0.93
     becauſe
    -0.93
    POSITIVE LOGITS
    CodeAnalysis
    0.84
    typeorm
    0.83
     fraude
    0.77
     Hoop
    0.75
    hy
    0.70
    TextAppearance
    0.67
    rom
    0.65
    ONYMOUS
    0.65
     Pogba
    0.63
     hypoxia
    0.63
    Act Density 0.486%

    No Known Activations