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

    Neuronpedia

    INDEX
    Explanations

    verbs associated with compliance, agreement, and participation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     âĵĺ
    -0.58
    unless
    -0.56
    mpire
    -0.56
    %);
    -0.56
     awaiting
    -0.55
     reckoned
    -0.54
     tending
    -0.54
    although
    -0.54
     enthusi
    -0.53
     Niet
    -0.53
    POSITIVE LOGITS
    ilipp
    0.67
     these
    0.63
    ealous
    0.62
     guiActive
    0.61
     outward
    0.60
    ¿½
    0.60
     yourself
    0.60
    irtual
    0.60
     hindsight
    0.59
    estial
    0.58
    Act Density 0.053%

    No Known Activations