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

    Neuronpedia

    INDEX
    Explanations

    words related to video game abilities and names

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     intrusion
    -0.64
     reinforcement
    -0.63
     GEAR
    -0.62
     Resolution
    -0.61
     Engineers
    -0.60
     Gems
    -0.59
    INGTON
    -0.58
    etheless
    -0.58
     Voltage
    -0.57
     Kend
    -0.57
    POSITIVE LOGITS
    gemony
    1.19
    resy
    1.19
    arer
    1.16
    lder
    1.16
    aven
    1.15
    zbollah
    1.15
    ALTH
    1.13
    ather
    1.11
    uristic
    1.10
    arers
    1.09
    Act Density 0.065%

    No Known Activations