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

    Neuronpedia

    INDEX
    Explanations

    words related to thoughts, feelings, and emotions

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    quished
    -0.75
    Lago
    -0.68
    Ann
    -0.68
    Universal
    -0.66
    ça
    -0.65
    ylon
    -0.65
    vernment
    -0.64
    interrupted
    -0.64
     Ster
    -0.64
     Parenthood
    -0.63
    POSITIVE LOGITS
     deeds
    1.40
     feelings
    1.33
     deed
    1.29
     actions
    1.27
     prayers
    1.19
     impulses
    1.19
     emotions
    1.16
     intentions
    1.16
     behaviors
    1.12
     conscience
    1.10
    Act Density 0.158%

    No Known Activations