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

    Neuronpedia

    INDEX
    Explanations

    terms related to positive experiences and emotions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     cuánt
    -0.62
    thschild
    -0.61
    __["
    -0.58
    BK
    -0.58
     Métro
    -0.57
    import
    -0.57
    wahati
    -0.56
    illots
    -0.56
    Hutch
    -0.56
    gesehen
    -0.56
    POSITIVE LOGITS
     positive
    2.37
     Positive
    2.27
    Positive
    2.23
     POSITIVE
    2.19
    positive
    2.12
    POSITIVE
    2.02
     Posi
    1.99
     positives
    1.98
     positif
    1.85
     positivity
    1.82
    Act Density 0.093%

    No Known Activations