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

    Neuronpedia

    INDEX
    Explanations

    concepts related to collective memory and progress in historical narratives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     fake
    -0.15
    à¹Ĥà¸ķ
    -0.15
    iene
    -0.15
     tostring
    -0.14
    fake
    -0.14
    aug
    -0.14
    su
    -0.14
    zung
    -0.14
    pty
    -0.13
     illusion
    -0.13
    POSITIVE LOGITS
     sub
    0.53
     uncon
    0.43
     subconscious
    0.41
     unconscious
    0.40
     Sub
    0.35
    sub
    0.35
    .sub
    0.31
    Sub
    0.30
    _sub
    0.30
    (sub
    0.28
    Act Density 0.482%

    No Known Activations