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

    Neuronpedia

    INDEX
    Explanations

    references to emotions and psychological states

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    twimg
    -0.80
    Manbalar
    -0.80
    ագրություններ
    -0.77
    Sklici
    -0.76
    InputBorder
    -0.73
    olingo
    -0.73
     
    -0.71
    ädie
    -0.70
    BagConstraints
    -0.70
    Искәрмәләр
    -0.68
    POSITIVE LOGITS
     fondi
    0.60
     gradualmente
    0.56
    #
    0.55
     gewel
    0.54
     vinto
    0.53
     nagu
    0.52
    terase
    0.50
     dovrebbero
    0.49
     ordinaria
    0.49
     préparé
    0.49
    Act Density 0.495%

    No Known Activations