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

    Neuronpedia

    INDEX
    Explanations

    references to specific individuals, particularly in the context of media or public figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ViewInit
    -0.60
     Bewußt
    -0.57
     uș
    -0.56
     vacacionales
    -0.56
     térmico
    -0.55
    ExtendWith
    -0.55
     odeur
    -0.54
    Jîn
    -0.54
     sanitarias
    -0.54
     redacción
    -0.52
    POSITIVE LOGITS
     TZ
    0.47
     (“
    0.46
     
    0.44
     (&
    0.42
     Fucking
    0.42
     「
    0.42
     (‘
    0.40
     («
    0.40
     consultato
    0.39
     ("
    0.39
    Act Density 0.448%

    No Known Activations