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

    Neuronpedia

    INDEX
    Explanations

    numbers related to quantities or measurements

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     CAM
    -0.71
     AUD
    -0.67
     TAG
    -0.67
     camping
    -0.65
     Ember
    -0.64
     Hass
    -0.64
     Soldiers
    -0.63
     ever
    -0.63
     McGill
    -0.62
     Alexandra
    -0.60
    POSITIVE LOGITS
    5
    1.14
    35
    1.09
    8
    1.09
    25
    1.09
    6
    1.08
    7
    1.08
    26
    1.08
    16
    1.07
    05
    1.07
    45
    1.07
    Act Density 0.060%

    No Known Activations