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

    Neuronpedia

    INDEX
    Explanations

    words that end with the suffix 'ly'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     altrett
    -0.57
    cette
    -0.54
     absolute
    -0.53
    absolute
    -0.53
     ripar
    -0.51
     cuantos
    -0.51
     Hildebrand
    -0.50
     inevit
    -0.50
    ophor
    -0.50
     whose
    -0.50
    POSITIVE LOGITS
    vably
    1.13
    ently
    1.12
    ously
    1.05
    denly
    1.00
    atically
    0.98
    AsUp
    0.97
    ATELY
    0.96
    cerely
    0.96
    tically
    0.95
    ially
    0.94
    Act Density 0.201%

    No Known Activations