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

    Neuronpedia

    INDEX
    Explanations

    quantities or measurements mentioned in barrels, tons, or units

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    laus
    -0.81
    uthor
    -0.67
    Parent
    -0.66
     mull
    -0.65
     Practices
    -0.65
     befriend
    -0.64
     Username
    -0.61
    hari
    -0.61
     Targ
    -0.61
     Approach
    -0.59
    POSITIVE LOGITS
     usable
    1.04
    cible
    0.85
     payload
    0.83
     useful
    0.82
     quantities
    0.78
    aganda
    0.77
     surplus
    0.77
     output
    0.77
     outputs
    0.77
     valuable
    0.75
    Act Density 0.243%

    No Known Activations