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

    Neuronpedia

    INDEX
    Explanations

    words related to technology and manipulation, such as hologram, manipulates, robot, and antennas

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to manipulation or transformation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ]."
    -0.74
     sqor
    -0.71
    ]).
    -0.64
    vironment
    -0.60
    APD
    -0.59
    Contract
    -0.58
     Accountability
    -0.58
    ģ«
    -0.57
    heimer
    -0.57
    ].
    -0.56
    POSITIVE LOGITS
     translucent
    0.66
     protr
    0.64
     Shutterstock
    0.60
     chlorine
    0.59
     fins
    0.59
     centrif
    0.58
    epad
    0.58
    icho
    0.56
     rectangular
    0.55
     seaw
    0.55
    Act Density 1.715%

    No Known Activations