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

    Neuronpedia

    INDEX
    Explanations

    actions related to rolling or movement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Jeffries
    -0.77
     Prieto
    -0.75
     Schen
    -0.67
     Schenk
    -0.66
    ricio
    -0.65
    oggetto
    -0.63
     sujet
    -0.61
     Figue
    -0.61
    ̷
    -0.60
    ences
    -0.59
    POSITIVE LOGITS
     roll
    1.76
     ROLL
    1.75
     rolls
    1.73
     Roll
    1.69
     Rolls
    1.65
    roll
    1.59
    ROLL
    1.59
    Roll
    1.58
    Rolls
    1.52
     rolling
    1.46
    Act Density 0.057%

    No Known Activations