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

    Neuronpedia

    INDEX
    Explanations

    phrases related to various forms of conflict or instability

    oai_token-act-pair · gpt-3.5-turbo

    the word "on" in various contexts throughout the document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    MODE
    -0.87
    DragonMagazine
    -0.86
    BIP
    -0.80
    SourceFile
    -0.78
    Cod
    -0.72
    ACT
    -0.72
    Champ
    -0.71
    RECT
    -0.71
    Shield
    -0.71
    Apps
    -0.70
    POSITIVE LOGITS
     behalf
    1.52
    erous
    1.27
    shore
    1.07
    etime
    1.00
    site
    0.97
     steroids
    0.95
     occasion
    0.92
    coming
    0.92
    yx
    0.92
    anism
    0.90
    Act Density 0.349%

    No Known Activations