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

    Neuronpedia

    INDEX
    Explanations

    expressions of feelings related to authenticity and belonging

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    svet
    -0.69
     démocr
    -0.54
    peper
    -0.52
     sagesse
    -0.52
     muka
    -0.52
    INGHAM
    -0.51
    ciach
    -0.51
    velocityY
    -0.51
     flèche
    -0.51
     extré
    -0.50
    POSITIVE LOGITS
     uneasy
    0.65
     >=",
    0.60
    Clik
    0.60
     Numerade
    0.59
    مصادر
    0.58
     uneasiness
    0.56
     restless
    0.56
     nagging
    0.55
    ⓧ
    0.55
    givings
    0.55
    Act Density 0.320%

    No Known Activations