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

    Neuronpedia

    INDEX
    Explanations

    markers indicating the beginning of text or sections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     unknownFields
    -0.54
    SceneManagement
    -0.48
     and
    -0.48
    #![
    -0.47
    velocityY
    -0.47
    ád
    -0.46
     case
    -0.46
    ectoria
    -0.45
    case
    -0.43
    inj
    -0.42
    POSITIVE LOGITS
    TagMode
    0.86
     replying
    0.80
    enumi
    0.74
     Forumite
    0.72
     Efq
    0.72
     doubtnut
    0.71
     moderator
    0.71
     AssemblyProduct
    0.71
     replied
    0.70
    ^(@)
    0.69
    Act Density 0.110%

    No Known Activations