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

    Neuronpedia

    INDEX
    Explanations

    imperative sentences

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate urgency or importance in communication

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    *.
    -0.46
    acea
    -0.45
    azard
    -0.44
    appropriately
    -0.44
    $.
    -0.42
    luster
    -0.41
    anism
    -0.41
    interstitial
    -0.41
     undermin
    -0.41
    alist
    -0.40
    POSITIVE LOGITS
     however
    0.67
     meanwhile
    0.53
     though
    0.47
     therefore
    0.46
     moreover
    0.45
     Nek
    0.41
     also
    0.41
     tho
    0.41
    .--
    0.40
     Hide
    0.40
    Act Density 3.187%

    No Known Activations