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

    Neuronpedia

    INDEX
    Explanations

    dates written either partially or fully

    oai_token-act-pair · gpt-3.5-turbo

    dates and numerical values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    CN
    -0.73
    20439
    -0.73
     BF
    -0.72
    ãĥ¼ãĥĨ
    -0.67
    ãĥķãĤ¡
    -0.66
    accompan
    -0.65
     Horus
    -0.65
    DragonMagazine
    -0.61
    yout
    -0.61
     HRC
    -0.60
    POSITIVE LOGITS
    ommel
    0.71
    sterdam
    0.67
     strut
    0.67
    roma
    0.66
    utterstock
    0.66
    tick
    0.65
    irk
    0.64
     reminis
    0.61
    verb
    0.60
    akedown
    0.59
    Act Density 0.081%

    No Known Activations