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

    Neuronpedia

    INDEX
    Explanations

    words and phrases related to personal experiences and emotions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Efq
    -0.91
    AddTagHelper
    -0.91
     للمعارف
    -0.86
     Cæsar
    -0.85
     avoient
    -0.84
    AutoresizingMask
    -0.82
     صوتيه
    -0.82
     plainte
    -0.81
     normaux
    -0.80
     Monfieur
    -0.80
    POSITIVE LOGITS
     “
    0.98
     "
    0.73
     he
    0.62
     one
    0.59
     
    0.58
     «
    0.56
    ProcessEvent
    0.53
     plans
    0.51
    ,
    0.51
    。「
    0.51
    Act Density 0.323%

    No Known Activations