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

    Neuronpedia

    INDEX
    Explanations

    the word "that" occurring as a conjunction in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Jefus
    -0.85
    ſelves
    -0.83
     pleaſure
    -0.80
     vectorstock
    -0.77
    ſelf
    -0.77
     houſe
    -0.77
     chofe
    -0.75
     ſtate
    -0.75
     moschino
    -0.74
     bershka
    -0.74
    POSITIVE LOGITS
     чтобы
    0.53
     (
    0.52
    номер
    0.50
     enable
    0.47
    addPreferredGap
    0.47
     suitable
    0.47
    ,
    0.47
     for
    0.47
    enabled
    0.46
     help
    0.45
    Act Density 0.120%

    No Known Activations