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

    Neuronpedia

    INDEX
    Explanations

    concepts related to processes of facilitation, modification, and termination

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Comes before prepositions/determiners

    np_acts-logits-general · gemini-2.0-flash

    ending or purpose

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ness
    -0.89
    ings
    -0.80
    iness
    -0.80
    est
    -0.73
    c
    -0.64
    -
    -0.63
    lec
    -0.62
    room
    -0.61
    ish
    -0.60
    ể
    -0.60
    POSITIVE LOGITS
     myſelf
    1.38
     itſelf
    1.28
     themſelves
    1.18
     himſelf
    1.08
     ſeveral
    1.05
     pleaſure
    1.03
     purpoſe
    1.02
     againſt
    1.01
    ALLY
    0.98
     ―――――
    0.97
    Act Density 0.692%

    No Known Activations