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

    Neuronpedia

    INDEX
    Explanations

    actions and verbs related to moving, particularly "roll."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Jeffries
    -0.79
     Prieto
    -0.74
    oggetto
    -0.74
    andafter
    -0.71
     Schenk
    -0.70
    setImageBitmap
    -0.68
     dikutip
    -0.68
    ricio
    -0.67
    textTheme
    -0.66
    eniably
    -0.66
    POSITIVE LOGITS
     roll
    2.38
     rolls
    2.28
     Roll
    2.22
     ROLL
    2.20
    Roll
    2.11
    roll
    2.10
     rolled
    2.05
     rolling
    2.05
    ROLL
    1.97
     Rolls
    1.91
    Act Density 0.051%

    No Known Activations