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

    Neuronpedia

    INDEX
    Explanations

    numerical data and values in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     unders
    -0.76
     CAM
    -0.74
     polic
    -0.68
     shutter
    -0.66
     portrait
    -0.66
     purse
    -0.66
     framing
    -0.65
     cottage
    -0.65
     camer
    -0.65
     Alexandra
    -0.64
    POSITIVE LOGITS
    0
    1.23
    5
    1.22
    8
    1.10
    1
    1.09
    7
    1.07
    2
    1.07
    4
    1.05
    3
    1.05
    6
    1.03
    25
    1.00
    Act Density 0.024%

    No Known Activations