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

    Neuronpedia

    INDEX
    Explanations

    words with the suffix "-aying" or "-ayed"

    oai_token-act-pair · gpt-3.5-turbo

    words related to actions or states involving layering or straying

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     lever
    -0.61
     glob
    -0.60
     gag
    -0.59
     Tub
    -0.59
     constitu
    -0.58
     features
    -0.57
     fre
    -0.57
     mult
    -0.57
     Caps
    -0.56
     synth
    -0.55
    POSITIVE LOGITS
    aying
    4.21
    ayed
    2.80
    ays
    2.49
    ayers
    2.47
    ayer
    2.02
    ay
    1.78
    AY
    1.57
    aid
    1.49
    aye
    1.19
    ying
    1.13
    Act Density 0.010%

    No Known Activations