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

    Neuronpedia

    INDEX
    Explanations

    numerical values and associated symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Millar
    -0.64
    getDoctrine
    -0.64
    redients
    -0.59
    YON
    -0.57
    trange
    -0.56
    SSON
    -0.55
    nace
    -0.54
    VENUE
    -0.54
     venue
    -0.53
     Messina
    -0.53
    POSITIVE LOGITS
    6
    0.66
    2
    0.66
    1
    0.65
    3
    0.65
    7
    0.63
    5
    0.62
    0
    0.59
    8
    0.59
    9
    0.57
    4
    0.57
    Act Density 0.155%

    No Known Activations