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

    Neuronpedia

    INDEX
    Explanations

    words related to feelings or emotions, with a focus on positive or strong feelings

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    Glej
    -0.76
     enrique
    -0.67
     notori
    -0.67
    Pozri
    -0.66
     ridu
    -0.65
     DIOS
    -0.64
     vanta
    -0.63
     ALLA
    -0.63
     persua
    -0.63
    excelente
    -0.63
    POSITIVE LOGITS
     optik
    0.76
     öf
    0.60
     keramik
    0.60
     kafe
    0.58
     labd
    0.57
     kabát
    0.57
     mikrofon
    0.57
     kompakt
    0.57
     ekst
    0.56
     antik
    0.55
    Act Density 0.329%

    No Known Activations