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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and symbols indicating the end of sentences or phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    تقاوى
    -0.71
    LookAnd
    -0.65
     utafitiHapana
    -0.64
     resourceCulture
    -0.61
    setVerticalGroup
    -0.60
    ůli
    -0.60
     Roskov
    -0.59
    anthene
    -0.59
     createState
    -0.58
    İstinadlar
    -0.57
    POSITIVE LOGITS
    MessageTagHelper
    0.59
    <eos>
    0.54
     Cæsar
    0.53
     Reverso
    0.52
     recourse
    0.50
     straws
    0.50
    corer
    0.50
     Parenthood
    0.49
     techs
    0.49
    voyance
    0.49
    Act Density 0.180%

    No Known Activations