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

    Neuronpedia

    INDEX
    Explanations

    terms related to modifications or variations in regulatory contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     himſelf
    -1.45
     themſelves
    -1.41
     myſelf
    -1.41
    ſelves
    -1.36
     itſelf
    -1.32
    ſelf
    -1.30
     Eſ
    -1.24
     reaſon
    -1.23
     juſt
    -1.22
     whoſe
    -1.22
    POSITIVE LOGITS
    k
    0.84
    e
    0.83
    d
    0.81
     createState
    0.77
    m
    0.75
    u
    0.72
    t
    0.71
    p
    0.70
    l
    0.70
    n
    0.70
    Act Density 1.702%

    No Known Activations