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

    Neuronpedia

    INDEX
    Explanations

    references to the action of rolling or movement associated with rolling

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    the word "roll"

    np_acts-logits-general · gemini-2.0-flash

    roll your eyes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    OGND
    -0.60
     pior
    -0.56
    izr
    -0.55
    ibb
    -0.55
    iors
    -0.54
     Sparks
    -0.54
     gius
    -0.52
    pecker
    -0.50
    impresa
    -0.50
    yntaxException
    -0.50
    POSITIVE LOGITS
     rolls
    1.26
     roll
    1.22
     ROLL
    1.19
     Roll
    1.17
     rolling
    1.13
     rolled
    1.12
    Roll
    1.11
    roll
    1.08
    ROLL
    1.08
     Rol
    1.05
    Act Density 0.066%

    No Known Activations