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

    Neuronpedia

    INDEX
    Explanations

    concepts related to progress and momentum in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Walk
    -0.15
    ÙĤب
    -0.14
    ario
    -0.14
     backgrounds
    -0.14
    rient
    -0.14
     requis
    -0.14
     Background
    -0.13
    RIES
    -0.13
    .gdx
    -0.13
    .yy
    -0.13
    POSITIVE LOGITS
     momentum
    0.49
     Momentum
    0.38
    omentum
    0.35
     steam
    0.33
    steam
    0.28
     traction
    0.28
     acceleration
    0.27
     pace
    0.26
     gaining
    0.24
    moment
    0.23
    Act Density 0.201%

    No Known Activations